Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2737 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3117. Min Range: -7.3117
Max Act: 7.3117. Min Act: -0.1700
Data Index: 6420541 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3117. Min Range: -7.3117
Max Act: 7.3117. Min Act: -0.1700
Data Index: 433866 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3117. Min Range: -7.3117
Max Act: 7.3117. Min Act: -0.1700
Data Index: 5109786 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3117. Min Range: -7.3117
Max Act: 7.2179. Min Act: -0.1700
Data Index: 1499493 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3117. Min Range: -7.3117
Max Act: 7.2179. Min Act: -0.1700
Data Index: 8469302 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3117. Min Range: -7.3117
Max Act: 7.2179. Min Act: -0.1700
Data Index: 8439369 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3117. Min Range: -7.3117
Max Act: 7.1867. Min Act: -0.1700
Data Index: 359507 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3117. Min Range: -7.3117
Max Act: 7.1867. Min Act: -0.1700
Data Index: 6957586 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3117. Min Range: -7.3117
Max Act: 7.1554. Min Act: -0.1700
Data Index: 3418339 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3117. Min Range: -7.3117
Max Act: 7.1554. Min Act: -0.1700
Data Index: 5483570 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3117. Min Range: -7.3117
Max Act: 7.1242. Min Act: -0.1700
Data Index: 993796 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3117. Min Range: -7.3117
Max Act: 7.1242. Min Act: -0.1700
Data Index: 7479877 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3117. Min Range: -7.3117
Max Act: 7.1242. Min Act: -0.1700
Data Index: 124612 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3117. Min Range: -7.3117
Max Act: 7.0617. Min Act: -0.1700
Data Index: 7039866 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3117. Min Range: -7.3117
Max Act: 7.0617. Min Act: -0.1700
Data Index: 6283770 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3117. Min Range: -7.3117
Max Act: 7.0304. Min Act: -0.1700
Data Index: 3281982 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3117. Min Range: -7.3117
Max Act: 7.0304. Min Act: -0.1700
Data Index: 647791 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3117. Min Range: -7.3117
Max Act: 6.9992. Min Act: -0.1700
Data Index: 2535020 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3117. Min Range: -7.3117
Max Act: 6.9992. Min Act: -0.1700
Data Index: 1027773 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3117. Min Range: -7.3117
Max Act: 6.9679. Min Act: -0.1700
Data Index: 7692160 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19