Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5326 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3149. Min Range: -7.3149
Max Act: 7.3149. Min Act: -0.1700
Data Index: 7654695 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3149. Min Range: -7.3149
Max Act: 7.1587. Min Act: -0.1700
Data Index: 5658436 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3149. Min Range: -7.3149
Max Act: 7.0024. Min Act: -0.1700
Data Index: 2524388 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3149. Min Range: -7.3149
Max Act: 6.7837. Min Act: -0.1700
Data Index: 7406281 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3149. Min Range: -7.3149
Max Act: 6.7837. Min Act: -0.1700
Data Index: 5440416 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3149. Min Range: -7.3149
Max Act: 6.7212. Min Act: -0.1700
Data Index: 438971 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3149. Min Range: -7.3149
Max Act: 6.6899. Min Act: -0.1700
Data Index: 6620492 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3149. Min Range: -7.3149
Max Act: 6.6587. Min Act: -0.1700
Data Index: 5843879 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3149. Min Range: -7.3149
Max Act: 6.6899. Min Act: -0.1700
Data Index: 1767361 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3149. Min Range: -7.3149
Max Act: 6.6587. Min Act: -0.1700
Data Index: 6202045 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3149. Min Range: -7.3149
Max Act: 6.6274. Min Act: -0.1700
Data Index: 7442627 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3149. Min Range: -7.3149
Max Act: 6.6274. Min Act: -0.1700
Data Index: 4099785 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3149. Min Range: -7.3149
Max Act: 6.6274. Min Act: -0.1700
Data Index: 2157076 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3149. Min Range: -7.3149
Max Act: 6.6274. Min Act: -0.1700
Data Index: 8285611 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3149. Min Range: -7.3149
Max Act: 6.5962. Min Act: -0.1700
Data Index: 6786714 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3149. Min Range: -7.3149
Max Act: 6.5962. Min Act: -0.1700
Data Index: 4136927 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3149. Min Range: -7.3149
Max Act: 6.5962. Min Act: -0.1700
Data Index: 1664589 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3149. Min Range: -7.3149
Max Act: 6.5649. Min Act: -0.1700
Data Index: 5902881 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3149. Min Range: -7.3149
Max Act: 6.5337. Min Act: -0.1700
Data Index: 7034744 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3149. Min Range: -7.3149
Max Act: 6.5337. Min Act: -0.1700
Data Index: 2901700 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #19