Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1677 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7805. Min Range: -4.7805
Max Act: 4.7805. Min Act: -0.1700
Data Index: 5893374 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7805. Min Range: -4.7805
Max Act: 4.7180. Min Act: -0.1700
Data Index: 6285795 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7805. Min Range: -4.7805
Max Act: 4.6868. Min Act: -0.1700
Data Index: 1782016 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7805. Min Range: -4.7805
Max Act: 4.6868. Min Act: -0.1700
Data Index: 1096326 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7805. Min Range: -4.7805
Max Act: 4.6555. Min Act: -0.1700
Data Index: 3242539 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7805. Min Range: -4.7805
Max Act: 4.6555. Min Act: -0.1700
Data Index: 5949353 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7805. Min Range: -4.7805
Max Act: 4.6555. Min Act: -0.1700
Data Index: 8271079 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7805. Min Range: -4.7805
Max Act: 4.5618. Min Act: -0.1700
Data Index: 4081717 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7805. Min Range: -4.7805
Max Act: 4.5930. Min Act: -0.1700
Data Index: 164320 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7805. Min Range: -4.7805
Max Act: 4.5930. Min Act: -0.1700
Data Index: 3830220 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7805. Min Range: -4.7805
Max Act: 4.5930. Min Act: -0.1700
Data Index: 4802440 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7805. Min Range: -4.7805
Max Act: 4.5930. Min Act: -0.1700
Data Index: 7437602 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7805. Min Range: -4.7805
Max Act: 4.5618. Min Act: -0.1700
Data Index: 5729191 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7805. Min Range: -4.7805
Max Act: 4.5618. Min Act: -0.1700
Data Index: 3475587 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7805. Min Range: -4.7805
Max Act: 4.5305. Min Act: -0.1700
Data Index: 7676007 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7805. Min Range: -4.7805
Max Act: 4.5305. Min Act: -0.1700
Data Index: 8343435 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7805. Min Range: -4.7805
Max Act: 4.4993. Min Act: -0.1700
Data Index: 5493867 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7805. Min Range: -4.7805
Max Act: 4.5305. Min Act: -0.1700
Data Index: 1236779 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7805. Min Range: -4.7805
Max Act: 4.4680. Min Act: -0.1700
Data Index: 1480547 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7805. Min Range: -4.7805
Max Act: 4.4680. Min Act: -0.1700
Data Index: 3949971 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19