Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 573 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.6275. Min Act: -0.1700
Data Index: 995789 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.4088. Min Act: -0.1700
Data Index: 1061694 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.3150. Min Act: -0.1700
Data Index: 3408537 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.3463. Min Act: -0.1700
Data Index: 7236251 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.2838. Min Act: -0.1700
Data Index: 6132010 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.2838. Min Act: -0.1700
Data Index: 8787336 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.2838. Min Act: -0.1700
Data Index: 4829743 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.2525. Min Act: -0.1700
Data Index: 165546 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.1900. Min Act: -0.1700
Data Index: 7420333 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.1900. Min Act: -0.1700
Data Index: 8535820 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.1900. Min Act: -0.1700
Data Index: 1033099 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.1900. Min Act: -0.1700
Data Index: 6052899 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.1275. Min Act: -0.1700
Data Index: 6610834 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.1588. Min Act: -0.1700
Data Index: 2372941 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.1275. Min Act: -0.1700
Data Index: 6314020 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.0963. Min Act: -0.1700
Data Index: 4355861 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.1275. Min Act: -0.1700
Data Index: 806376 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.1275. Min Act: -0.1700
Data Index: 6863425 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.0963. Min Act: -0.1700
Data Index: 4441603 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6275. Min Range: -6.6275
Max Act: 6.0963. Min Act: -0.1700
Data Index: 1837438 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #19