Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2707 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1628. Min Range: -7.1628
Max Act: 7.1628. Min Act: -0.1700
Data Index: 894342 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1628. Min Range: -7.1628
Max Act: 7.1003. Min Act: -0.1700
Data Index: 1317476 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1628. Min Range: -7.1628
Max Act: 7.0378. Min Act: -0.1700
Data Index: 4469661 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1628. Min Range: -7.1628
Max Act: 7.0378. Min Act: -0.1700
Data Index: 5885752 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1628. Min Range: -7.1628
Max Act: 7.0378. Min Act: -0.1700
Data Index: 3100387 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1628. Min Range: -7.1628
Max Act: 6.9753. Min Act: -0.1700
Data Index: 53527 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1628. Min Range: -7.1628
Max Act: 6.9441. Min Act: -0.1700
Data Index: 1540408 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1628. Min Range: -7.1628
Max Act: 6.8503. Min Act: -0.1700
Data Index: 926926 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1628. Min Range: -7.1628
Max Act: 6.8816. Min Act: -0.1700
Data Index: 1319665 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1628. Min Range: -7.1628
Max Act: 6.8816. Min Act: -0.1700
Data Index: 8654617 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1628. Min Range: -7.1628
Max Act: 6.8503. Min Act: -0.1700
Data Index: 8578468 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1628. Min Range: -7.1628
Max Act: 6.8191. Min Act: -0.1700
Data Index: 1540409 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1628. Min Range: -7.1628
Max Act: 6.8191. Min Act: -0.1700
Data Index: 1982000 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1628. Min Range: -7.1628
Max Act: 6.8191. Min Act: -0.1700
Data Index: 3639452 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1628. Min Range: -7.1628
Max Act: 6.8191. Min Act: -0.1700
Data Index: 6069262 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1628. Min Range: -7.1628
Max Act: 6.8191. Min Act: -0.1700
Data Index: 6601331 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1628. Min Range: -7.1628
Max Act: 6.7878. Min Act: -0.1700
Data Index: 3559032 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1628. Min Range: -7.1628
Max Act: 6.7253. Min Act: -0.1700
Data Index: 7672125 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1628. Min Range: -7.1628
Max Act: 6.6941. Min Act: -0.1700
Data Index: 892086 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1628. Min Range: -7.1628
Max Act: 6.7253. Min Act: -0.1700
Data Index: 3639453 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19