Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1786 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5176. Min Range: -8.5176
Max Act: 8.5176. Min Act: -0.1700
Data Index: 3390138 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5176. Min Range: -8.5176
Max Act: 8.3926. Min Act: -0.1700
Data Index: 2131943 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5176. Min Range: -8.5176
Max Act: 8.3301. Min Act: -0.1700
Data Index: 1924794 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5176. Min Range: -8.5176
Max Act: 8.2051. Min Act: -0.1700
Data Index: 1021615 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5176. Min Range: -8.5176
Max Act: 8.2051. Min Act: -0.1700
Data Index: 8738088 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5176. Min Range: -8.5176
Max Act: 8.2051. Min Act: -0.1700
Data Index: 7779992 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5176. Min Range: -8.5176
Max Act: 8.1426. Min Act: -0.1700
Data Index: 2698769 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5176. Min Range: -8.5176
Max Act: 8.1426. Min Act: -0.1700
Data Index: 7589525 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5176. Min Range: -8.5176
Max Act: 8.1426. Min Act: -0.1700
Data Index: 888734 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5176. Min Range: -8.5176
Max Act: 8.1426. Min Act: -0.1700
Data Index: 1931834 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5176. Min Range: -8.5176
Max Act: 8.0801. Min Act: -0.1700
Data Index: 2069017 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5176. Min Range: -8.5176
Max Act: 8.0801. Min Act: -0.1700
Data Index: 1773594 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5176. Min Range: -8.5176
Max Act: 8.0801. Min Act: -0.1700
Data Index: 4879833 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5176. Min Range: -8.5176
Max Act: 8.0801. Min Act: -0.1700
Data Index: 4038656 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5176. Min Range: -8.5176
Max Act: 8.0801. Min Act: -0.1700
Data Index: 3753104 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5176. Min Range: -8.5176
Max Act: 8.0176. Min Act: -0.1700
Data Index: 125580 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5176. Min Range: -8.5176
Max Act: 8.0176. Min Act: -0.1700
Data Index: 5833860 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5176. Min Range: -8.5176
Max Act: 8.0176. Min Act: -0.1700
Data Index: 2862658 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5176. Min Range: -8.5176
Max Act: 8.0176. Min Act: -0.1700
Data Index: 8361705 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5176. Min Range: -8.5176
Max Act: 8.0176. Min Act: -0.1700
Data Index: 6967910 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19