Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 441 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.8709. Min Act: -0.1700
Data Index: 5007676 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.6834. Min Act: -0.1700
Data Index: 6756236 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.5897. Min Act: -0.1700
Data Index: 7004456 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.5584. Min Act: -0.1700
Data Index: 1870525 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.5897. Min Act: -0.1700
Data Index: 3145670 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.5584. Min Act: -0.1700
Data Index: 7188701 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.5584. Min Act: -0.1700
Data Index: 4217403 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.5584. Min Act: -0.1700
Data Index: 2555893 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.5584. Min Act: -0.1700
Data Index: 3984657 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.5272. Min Act: -0.1700
Data Index: 200434 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.5272. Min Act: -0.1700
Data Index: 1279925 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.4959. Min Act: -0.1700
Data Index: 3217872 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.5584. Min Act: -0.1700
Data Index: 7246546 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.4959. Min Act: -0.1700
Data Index: 8670183 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.5272. Min Act: -0.1700
Data Index: 2237984 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.5272. Min Act: -0.1700
Data Index: 3215957 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.4959. Min Act: -0.1700
Data Index: 7209852 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.4959. Min Act: -0.1700
Data Index: 1821246 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.4959. Min Act: -0.1700
Data Index: 3503119 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8709. Min Range: -5.8709
Max Act: 5.4959. Min Act: -0.1700
Data Index: 7648040 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19