Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1064 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0323. Min Range: -7.0323
Max Act: 7.0323. Min Act: -0.1700
Data Index: 2858560 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0323. Min Range: -7.0323
Max Act: 7.0010. Min Act: -0.1700
Data Index: 5164775 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0323. Min Range: -7.0323
Max Act: 7.0323. Min Act: -0.1700
Data Index: 558822 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0323. Min Range: -7.0323
Max Act: 7.0010. Min Act: -0.1700
Data Index: 6162377 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0323. Min Range: -7.0323
Max Act: 6.9698. Min Act: -0.1700
Data Index: 787581 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0323. Min Range: -7.0323
Max Act: 6.8448. Min Act: -0.1700
Data Index: 3466019 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0323. Min Range: -7.0323
Max Act: 6.7823. Min Act: -0.1700
Data Index: 3222674 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0323. Min Range: -7.0323
Max Act: 6.8135. Min Act: -0.1700
Data Index: 7334403 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0323. Min Range: -7.0323
Max Act: 6.8135. Min Act: -0.1700
Data Index: 1919598 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0323. Min Range: -7.0323
Max Act: 6.8135. Min Act: -0.1700
Data Index: 3567193 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0323. Min Range: -7.0323
Max Act: 6.7823. Min Act: -0.1700
Data Index: 726209 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0323. Min Range: -7.0323
Max Act: 6.7510. Min Act: -0.1700
Data Index: 5987389 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0323. Min Range: -7.0323
Max Act: 6.7510. Min Act: -0.1700
Data Index: 8711884 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0323. Min Range: -7.0323
Max Act: 6.7198. Min Act: -0.1700
Data Index: 6038753 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0323. Min Range: -7.0323
Max Act: 6.7198. Min Act: -0.1700
Data Index: 4247123 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0323. Min Range: -7.0323
Max Act: 6.6885. Min Act: -0.1700
Data Index: 8246195 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0323. Min Range: -7.0323
Max Act: 6.6885. Min Act: -0.1700
Data Index: 7410500 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0323. Min Range: -7.0323
Max Act: 6.6573. Min Act: -0.1700
Data Index: 5781514 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0323. Min Range: -7.0323
Max Act: 6.6573. Min Act: -0.1700
Data Index: 4336113 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0323. Min Range: -7.0323
Max Act: 6.6260. Min Act: -0.1700
Data Index: 2052575 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19