Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1280 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.3771. Min Range: -6.3771
Max Act: 6.3771. Min Act: -0.1700
Data Index: 5223265 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3771. Min Range: -6.3771
Max Act: 6.3459. Min Act: -0.1700
Data Index: 7797469 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3771. Min Range: -6.3771
Max Act: 6.2834. Min Act: -0.1700
Data Index: 7385649 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3771. Min Range: -6.3771
Max Act: 6.3146. Min Act: -0.1700
Data Index: 6095857 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3771. Min Range: -6.3771
Max Act: 6.2209. Min Act: -0.1700
Data Index: 2425442 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3771. Min Range: -6.3771
Max Act: 6.2209. Min Act: -0.1700
Data Index: 4594682 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3771. Min Range: -6.3771
Max Act: 6.2209. Min Act: -0.1700
Data Index: 5534243 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3771. Min Range: -6.3771
Max Act: 6.2209. Min Act: -0.1700
Data Index: 1827159 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3771. Min Range: -6.3771
Max Act: 6.2209. Min Act: -0.1700
Data Index: 5704724 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3771. Min Range: -6.3771
Max Act: 6.1896. Min Act: -0.1700
Data Index: 5949429 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3771. Min Range: -6.3771
Max Act: 6.1896. Min Act: -0.1700
Data Index: 739171 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3771. Min Range: -6.3771
Max Act: 6.1896. Min Act: -0.1700
Data Index: 8544253 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3771. Min Range: -6.3771
Max Act: 6.1584. Min Act: -0.1700
Data Index: 922162 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3771. Min Range: -6.3771
Max Act: 6.1584. Min Act: -0.1700
Data Index: 5356511 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3771. Min Range: -6.3771
Max Act: 6.1271. Min Act: -0.1700
Data Index: 5203867 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3771. Min Range: -6.3771
Max Act: 6.1271. Min Act: -0.1700
Data Index: 904080 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3771. Min Range: -6.3771
Max Act: 6.0959. Min Act: -0.1700
Data Index: 6191065 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3771. Min Range: -6.3771
Max Act: 6.0959. Min Act: -0.1700
Data Index: 3147795 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3771. Min Range: -6.3771
Max Act: 6.0646. Min Act: -0.1700
Data Index: 531669 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3771. Min Range: -6.3771
Max Act: 6.0646. Min Act: -0.1700
Data Index: 6054794 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19