Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 634 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.8472. Min Act: -0.1700
Data Index: 1073823 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.8472. Min Act: -0.1700
Data Index: 2196693 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.8160. Min Act: -0.1700
Data Index: 3141910 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.7535. Min Act: -0.1700
Data Index: 7280429 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.7222. Min Act: -0.1700
Data Index: 6318175 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.7222. Min Act: -0.1700
Data Index: 8170490 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.6910. Min Act: -0.1700
Data Index: 4207962 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.6597. Min Act: -0.1700
Data Index: 688872 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5972. Min Act: -0.1700
Data Index: 2922720 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5972. Min Act: -0.1700
Data Index: 5449005 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5660. Min Act: -0.1700
Data Index: 5543558 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5972. Min Act: -0.1700
Data Index: 2691910 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5972. Min Act: -0.1700
Data Index: 3536320 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5660. Min Act: -0.1700
Data Index: 7370717 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5035. Min Act: -0.1700
Data Index: 5930907 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5347. Min Act: -0.1700
Data Index: 926926 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5347. Min Act: -0.1700
Data Index: 4452079 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5347. Min Act: -0.1700
Data Index: 1134058 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5035. Min Act: -0.1700
Data Index: 5399999 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8472. Min Range: -5.8472
Max Act: 5.5035. Min Act: -0.1700
Data Index: 5950333 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #19