Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2001 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1776. Min Range: -6.1776
Max Act: 6.1776. Min Act: -0.1700
Data Index: 4826164 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1776. Min Range: -6.1776
Max Act: 6.1463. Min Act: -0.1700
Data Index: 3201271 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1776. Min Range: -6.1776
Max Act: 6.1151. Min Act: -0.1700
Data Index: 1478044 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1776. Min Range: -6.1776
Max Act: 6.1151. Min Act: -0.1700
Data Index: 6780131 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1776. Min Range: -6.1776
Max Act: 6.1151. Min Act: -0.1700
Data Index: 3226643 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1776. Min Range: -6.1776
Max Act: 6.0526. Min Act: -0.1700
Data Index: 2681762 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1776. Min Range: -6.1776
Max Act: 6.0526. Min Act: -0.1700
Data Index: 5721402 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1776. Min Range: -6.1776
Max Act: 6.0213. Min Act: -0.1700
Data Index: 6862697 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1776. Min Range: -6.1776
Max Act: 6.0526. Min Act: -0.1700
Data Index: 3058638 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1776. Min Range: -6.1776
Max Act: 6.0213. Min Act: -0.1700
Data Index: 761074 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1776. Min Range: -6.1776
Max Act: 6.0213. Min Act: -0.1700
Data Index: 4520034 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1776. Min Range: -6.1776
Max Act: 6.0213. Min Act: -0.1700
Data Index: 4706175 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1776. Min Range: -6.1776
Max Act: 6.0213. Min Act: -0.1700
Data Index: 8770006 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1776. Min Range: -6.1776
Max Act: 5.9901. Min Act: -0.1700
Data Index: 1019108 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1776. Min Range: -6.1776
Max Act: 5.9588. Min Act: -0.1700
Data Index: 5951321 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1776. Min Range: -6.1776
Max Act: 5.9588. Min Act: -0.1700
Data Index: 4872175 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1776. Min Range: -6.1776
Max Act: 5.9588. Min Act: -0.1700
Data Index: 6548790 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1776. Min Range: -6.1776
Max Act: 5.9276. Min Act: -0.1700
Data Index: 4718284 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1776. Min Range: -6.1776
Max Act: 5.8963. Min Act: -0.1700
Data Index: 6220995 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1776. Min Range: -6.1776
Max Act: 5.9276. Min Act: -0.1700
Data Index: 2861825 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19