Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 644 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9443. Min Range: -7.9443
Max Act: 7.9443. Min Act: -0.1700
Data Index: 6944970 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9443. Min Range: -7.9443
Max Act: 7.8818. Min Act: -0.1700
Data Index: 6324001 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9443. Min Range: -7.9443
Max Act: 7.7568. Min Act: -0.1700
Data Index: 6944968 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9443. Min Range: -7.9443
Max Act: 7.5693. Min Act: -0.1700
Data Index: 5072051 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9443. Min Range: -7.9443
Max Act: 7.5068. Min Act: -0.1700
Data Index: 4994625 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9443. Min Range: -7.9443
Max Act: 7.5068. Min Act: -0.1700
Data Index: 7355165 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9443. Min Range: -7.9443
Max Act: 7.4755. Min Act: -0.1700
Data Index: 6380494 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9443. Min Range: -7.9443
Max Act: 7.4755. Min Act: -0.1699
Data Index: 267164 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9443. Min Range: -7.9443
Max Act: 7.4130. Min Act: -0.1700
Data Index: 8479237 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9443. Min Range: -7.9443
Max Act: 7.4130. Min Act: -0.1700
Data Index: 7902165 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9443. Min Range: -7.9443
Max Act: 7.4130. Min Act: -0.1700
Data Index: 5658967 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9443. Min Range: -7.9443
Max Act: 7.3818. Min Act: -0.1700
Data Index: 5597394 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9443. Min Range: -7.9443
Max Act: 7.3818. Min Act: -0.1700
Data Index: 185260 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9443. Min Range: -7.9443
Max Act: 7.3193. Min Act: -0.1700
Data Index: 4955919 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9443. Min Range: -7.9443
Max Act: 7.3193. Min Act: -0.1700
Data Index: 6071889 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9443. Min Range: -7.9443
Max Act: 7.3193. Min Act: -0.1700
Data Index: 6669737 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9443. Min Range: -7.9443
Max Act: 7.3193. Min Act: -0.1700
Data Index: 4899243 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9443. Min Range: -7.9443
Max Act: 7.2880. Min Act: -0.1700
Data Index: 6496572 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9443. Min Range: -7.9443
Max Act: 7.3505. Min Act: -0.1700
Data Index: 3668432 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9443. Min Range: -7.9443
Max Act: 7.2880. Min Act: -0.1700
Data Index: 1279502 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19