Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4290 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9591. Min Range: -7.9591
Max Act: 7.9591. Min Act: -0.1700
Data Index: 4837854 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9591. Min Range: -7.9591
Max Act: 7.8341. Min Act: -0.1700
Data Index: 903043 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9591. Min Range: -7.9591
Max Act: 7.6466. Min Act: -0.1700
Data Index: 6785033 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9591. Min Range: -7.9591
Max Act: 7.5841. Min Act: -0.1700
Data Index: 1486927 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9591. Min Range: -7.9591
Max Act: 7.5841. Min Act: -0.1700
Data Index: 7882860 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9591. Min Range: -7.9591
Max Act: 7.5216. Min Act: -0.1700
Data Index: 7987481 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9591. Min Range: -7.9591
Max Act: 7.3966. Min Act: -0.1700
Data Index: 6811598 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9591. Min Range: -7.9591
Max Act: 7.4278. Min Act: -0.1700
Data Index: 5009771 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9591. Min Range: -7.9591
Max Act: 7.4278. Min Act: -0.1700
Data Index: 5608123 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9591. Min Range: -7.9591
Max Act: 7.3966. Min Act: -0.1700
Data Index: 5278948 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9591. Min Range: -7.9591
Max Act: 7.3653. Min Act: -0.1700
Data Index: 8224941 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9591. Min Range: -7.9591
Max Act: 7.3653. Min Act: -0.1700
Data Index: 7664076 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9591. Min Range: -7.9591
Max Act: 7.3341. Min Act: -0.1700
Data Index: 3259410 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9591. Min Range: -7.9591
Max Act: 7.3341. Min Act: -0.1700
Data Index: 6733270 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9591. Min Range: -7.9591
Max Act: 7.3028. Min Act: -0.1700
Data Index: 4891676 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9591. Min Range: -7.9591
Max Act: 7.3341. Min Act: -0.1700
Data Index: 6655161 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9591. Min Range: -7.9591
Max Act: 7.3028. Min Act: -0.1700
Data Index: 6660776 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9591. Min Range: -7.9591
Max Act: 7.3028. Min Act: -0.1700
Data Index: 7643682 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9591. Min Range: -7.9591
Max Act: 7.2716. Min Act: -0.1700
Data Index: 7501992 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9591. Min Range: -7.9591
Max Act: 7.2716. Min Act: -0.1700
Data Index: 17156 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #19