Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3704 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1688. Min Range: -5.1688
Max Act: 5.1688. Min Act: -0.1700
Data Index: 1054561 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1688. Min Range: -5.1688
Max Act: 5.1375. Min Act: -0.1700
Data Index: 1054549 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1688. Min Range: -5.1688
Max Act: 5.0438. Min Act: -0.1700
Data Index: 7635008 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1688. Min Range: -5.1688
Max Act: 4.9813. Min Act: -0.1700
Data Index: 506644 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1688. Min Range: -5.1688
Max Act: 4.9188. Min Act: -0.1700
Data Index: 3637984 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1688. Min Range: -5.1688
Max Act: 4.9188. Min Act: -0.1700
Data Index: 3666542 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1688. Min Range: -5.1688
Max Act: 4.8250. Min Act: -0.1700
Data Index: 8051045 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1688. Min Range: -5.1688
Max Act: 4.7625. Min Act: -0.1700
Data Index: 3351907 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1688. Min Range: -5.1688
Max Act: 4.8250. Min Act: -0.1700
Data Index: 8078413 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1688. Min Range: -5.1688
Max Act: 4.7625. Min Act: -0.1700
Data Index: 1729910 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1688. Min Range: -5.1688
Max Act: 4.7625. Min Act: -0.1700
Data Index: 2126661 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1688. Min Range: -5.1688
Max Act: 4.7313. Min Act: -0.1700
Data Index: 4644826 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1688. Min Range: -5.1688
Max Act: 4.7313. Min Act: -0.1700
Data Index: 3754200 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1688. Min Range: -5.1688
Max Act: 4.7313. Min Act: -0.1700
Data Index: 5624725 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1688. Min Range: -5.1688
Max Act: 4.7313. Min Act: -0.1700
Data Index: 1001000 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1688. Min Range: -5.1688
Max Act: 4.7313. Min Act: -0.1700
Data Index: 7803432 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1688. Min Range: -5.1688
Max Act: 4.7000. Min Act: -0.1700
Data Index: 4549005 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1688. Min Range: -5.1688
Max Act: 4.7000. Min Act: -0.1700
Data Index: 4477265 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1688. Min Range: -5.1688
Max Act: 4.7313. Min Act: -0.1700
Data Index: 6641255 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1688. Min Range: -5.1688
Max Act: 4.7000. Min Act: -0.1700
Data Index: 5397973 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19