Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3842 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7973. Min Range: -3.7973
Max Act: 3.7973. Min Act: -0.1700
Data Index: 4078467 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7973. Min Range: -3.7973
Max Act: 3.5470. Min Act: -0.1700
Data Index: 3931107 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7973. Min Range: -3.7973
Max Act: 3.5470. Min Act: -0.1700
Data Index: 3093458 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7973. Min Range: -3.7973
Max Act: 3.5313. Min Act: -0.1700
Data Index: 5336969 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7973. Min Range: -3.7973
Max Act: 3.5157. Min Act: -0.1700
Data Index: 335048 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7973. Min Range: -3.7973
Max Act: 3.4843. Min Act: -0.1700
Data Index: 6602538 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7973. Min Range: -3.7973
Max Act: 3.5000. Min Act: -0.1700
Data Index: 3858960 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7973. Min Range: -3.7973
Max Act: 3.4843. Min Act: -0.1700
Data Index: 2762784 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7973. Min Range: -3.7973
Max Act: 3.4687. Min Act: -0.1700
Data Index: 6678328 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7973. Min Range: -3.7973
Max Act: 3.4687. Min Act: -0.1700
Data Index: 4024700 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7973. Min Range: -3.7973
Max Act: 3.4530. Min Act: -0.1700
Data Index: 2626644 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7973. Min Range: -3.7973
Max Act: 3.4373. Min Act: -0.1700
Data Index: 5178595 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7973. Min Range: -3.7973
Max Act: 3.4217. Min Act: -0.1700
Data Index: 1257266 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7973. Min Range: -3.7973
Max Act: 3.4373. Min Act: -0.1700
Data Index: 7783398 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7973. Min Range: -3.7973
Max Act: 3.4217. Min Act: -0.1700
Data Index: 6431224 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7973. Min Range: -3.7973
Max Act: 3.4217. Min Act: -0.1700
Data Index: 7207101 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7973. Min Range: -3.7973
Max Act: 3.4217. Min Act: -0.1700
Data Index: 2778524 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7973. Min Range: -3.7973
Max Act: 3.4060. Min Act: -0.1700
Data Index: 7826426 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7973. Min Range: -3.7973
Max Act: 3.3903. Min Act: -0.1700
Data Index: 2265276 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7973. Min Range: -3.7973
Max Act: 3.4060. Min Act: -0.1700
Data Index: 6793421 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19