Pith. sign in

REVIEW 3 cited by

Neurons in Large Language Models: Dead, N-gram, Positional

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2309.04827 v1 pith:46R3IJNL submitted 2023-09-09 cs.CL

classification cs.CL
keywords modelsneuronsdeadlargemanytokenactivateddata
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We analyze a family of large language models in such a lightweight manner that can be done on a single GPU. Specifically, we focus on the OPT family of models ranging from 125m to 66b parameters and rely only on whether an FFN neuron is activated or not. First, we find that the early part of the network is sparse and represents many discrete features. Here, many neurons (more than 70% in some layers of the 66b model) are "dead", i.e. they never activate on a large collection of diverse data. At the same time, many of the alive neurons are reserved for discrete features and act as token and n-gram detectors. Interestingly, their corresponding FFN updates not only promote next token candidates as could be expected, but also explicitly focus on removing the information about triggering them tokens, i.e., current input. To the best of our knowledge, this is the first example of mechanisms specialized at removing (rather than adding) information from the residual stream. With scale, models become more sparse in a sense that they have more dead neurons and token detectors. Finally, some neurons are positional: them being activated or not depends largely (or solely) on position and less so (or not at all) on textual data. We find that smaller models have sets of neurons acting as position range indicators while larger models operate in a less explicit manner.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SATORI: Static Test Oracle Generation for REST APIs

    cs.SE 2025-08 unverdicted novelty 5.0 of 10

    SATORI statically infers REST API test oracles from OpenAPI specs via LLMs, reporting F1 74.3%, above AGORA+'s 69.3%, with 18 confirmed bugs; the supplied full text, however, is a different paper.

  2. Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models

    cs.CL 2025-07 conditional novelty 5.0 of 10

    Pruning the most attribution-prominent MLP neurons in a single layer, chosen via a 10-sample validation sweep, consistently improves multiple-choice accuracy across four instruction-tuned LLMs.

  3. $\mu$-MoE: Test-Time Pruning as Micro-Grained Mixture-of-Experts

    cs.LG 2025-05 conditional novelty 4.0 of 10

    Test-time Wanda pruning, reframed as a mixture of micro-experts, adapts the sparse weight mask to each prompt and improves perplexity and VQA accuracy over static pruning baselines.

Pith tools