Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3371 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1517. Min Range: -8.1517
Max Act: 8.1517. Min Act: -0.1700
Data Index: 7205865 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1517. Min Range: -8.1517
Max Act: 7.9017. Min Act: -0.1700
Data Index: 4676521 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1517. Min Range: -8.1517
Max Act: 7.9017. Min Act: -0.1700
Data Index: 3512280 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1517. Min Range: -8.1517
Max Act: 7.8392. Min Act: -0.1700
Data Index: 876462 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1517. Min Range: -8.1517
Max Act: 7.7767. Min Act: -0.1700
Data Index: 4521451 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1517. Min Range: -8.1517
Max Act: 7.7142. Min Act: -0.1700
Data Index: 109292 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1517. Min Range: -8.1517
Max Act: 7.7142. Min Act: -0.1700
Data Index: 3026142 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1517. Min Range: -8.1517
Max Act: 7.7142. Min Act: -0.1700
Data Index: 2639878 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1517. Min Range: -8.1517
Max Act: 7.6517. Min Act: -0.1700
Data Index: 6392971 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1517. Min Range: -8.1517
Max Act: 7.6517. Min Act: -0.1700
Data Index: 4803747 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1517. Min Range: -8.1517
Max Act: 7.5892. Min Act: -0.1700
Data Index: 4665909 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1517. Min Range: -8.1517
Max Act: 7.4642. Min Act: -0.1700
Data Index: 8751508 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1517. Min Range: -8.1517
Max Act: 7.5267. Min Act: -0.1700
Data Index: 3830836 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1517. Min Range: -8.1517
Max Act: 7.5267. Min Act: -0.1700
Data Index: 1346660 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1517. Min Range: -8.1517
Max Act: 7.5267. Min Act: -0.1700
Data Index: 893440 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1517. Min Range: -8.1517
Max Act: 7.5267. Min Act: -0.1700
Data Index: 7775628 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1517. Min Range: -8.1517
Max Act: 7.4642. Min Act: -0.1700
Data Index: 880143 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1517. Min Range: -8.1517
Max Act: 7.4642. Min Act: -0.1700
Data Index: 27492 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1517. Min Range: -8.1517
Max Act: 7.4330. Min Act: -0.1700
Data Index: 3154474 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1517. Min Range: -8.1517
Max Act: 7.4642. Min Act: -0.1700
Data Index: 5804815 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #19