Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3491 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5971. Min Range: -10.5971
Max Act: 10.5971. Min Act: -0.1700
Data Index: 422905 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5971. Min Range: -10.5971
Max Act: 9.9721. Min Act: -0.1700
Data Index: 8237941 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5971. Min Range: -10.5971
Max Act: 9.9096. Min Act: -0.1700
Data Index: 3232915 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5971. Min Range: -10.5971
Max Act: 9.9096. Min Act: -0.1700
Data Index: 5807812 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5971. Min Range: -10.5971
Max Act: 9.8471. Min Act: -0.1700
Data Index: 8526190 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5971. Min Range: -10.5971
Max Act: 9.8471. Min Act: -0.1700
Data Index: 7717857 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5971. Min Range: -10.5971
Max Act: 9.7846. Min Act: -0.1700
Data Index: 1597865 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5971. Min Range: -10.5971
Max Act: 9.7221. Min Act: -0.1700
Data Index: 2972643 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5971. Min Range: -10.5971
Max Act: 9.7221. Min Act: -0.1700
Data Index: 1889650 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5971. Min Range: -10.5971
Max Act: 9.6596. Min Act: -0.1700
Data Index: 4120525 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5971. Min Range: -10.5971
Max Act: 9.6596. Min Act: -0.1700
Data Index: 5182950 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5971. Min Range: -10.5971
Max Act: 9.5971. Min Act: -0.1700
Data Index: 2445069 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5971. Min Range: -10.5971
Max Act: 9.4721. Min Act: -0.1700
Data Index: 3990127 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5971. Min Range: -10.5971
Max Act: 9.4096. Min Act: -0.1700
Data Index: 5175031 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5971. Min Range: -10.5971
Max Act: 9.4096. Min Act: -0.1700
Data Index: 1135121 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5971. Min Range: -10.5971
Max Act: 9.4096. Min Act: -0.1700
Data Index: 444621 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5971. Min Range: -10.5971
Max Act: 9.4096. Min Act: -0.1700
Data Index: 8691358 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5971. Min Range: -10.5971
Max Act: 9.4096. Min Act: -0.1700
Data Index: 7275017 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5971. Min Range: -10.5971
Max Act: 9.3471. Min Act: -0.1700
Data Index: 5171389 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5971. Min Range: -10.5971
Max Act: 9.2846. Min Act: -0.1700
Data Index: 2959979 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19