Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2689 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.6618. Min Range: -11.6618
Max Act: 11.6618. Min Act: -0.1700
Data Index: 5604446 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.6618. Min Range: -11.6618
Max Act: 10.9118. Min Act: -0.1700
Data Index: 755646 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.6618. Min Range: -11.6618
Max Act: 10.9118. Min Act: -0.1700
Data Index: 5691618 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.6618. Min Range: -11.6618
Max Act: 10.8493. Min Act: -0.1700
Data Index: 7453605 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.6618. Min Range: -11.6618
Max Act: 10.7243. Min Act: -0.1700
Data Index: 2665883 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.6618. Min Range: -11.6618
Max Act: 10.7243. Min Act: -0.1700
Data Index: 4503367 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.6618. Min Range: -11.6618
Max Act: 10.6618. Min Act: -0.1700
Data Index: 8143545 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.6618. Min Range: -11.6618
Max Act: 10.6618. Min Act: -0.1700
Data Index: 1841398 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.6618. Min Range: -11.6618
Max Act: 10.6618. Min Act: -0.1700
Data Index: 1383223 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.6618. Min Range: -11.6618
Max Act: 10.6618. Min Act: -0.1700
Data Index: 3061293 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.6618. Min Range: -11.6618
Max Act: 10.6618. Min Act: -0.1700
Data Index: 6999993 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.6618. Min Range: -11.6618
Max Act: 10.6618. Min Act: -0.1700
Data Index: 4503701 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.6618. Min Range: -11.6618
Max Act: 10.5993. Min Act: -0.1700
Data Index: 1749997 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.6618. Min Range: -11.6618
Max Act: 10.5368. Min Act: -0.1700
Data Index: 5070013 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.6618. Min Range: -11.6618
Max Act: 10.5368. Min Act: -0.1700
Data Index: 8039675 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.6618. Min Range: -11.6618
Max Act: 10.5993. Min Act: -0.1700
Data Index: 2302256 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.6618. Min Range: -11.6618
Max Act: 10.5993. Min Act: -0.1700
Data Index: 4213684 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.6618. Min Range: -11.6618
Max Act: 10.5993. Min Act: -0.1700
Data Index: 392098 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.6618. Min Range: -11.6618
Max Act: 10.5993. Min Act: -0.1700
Data Index: 2864328 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.6618. Min Range: -11.6618
Max Act: 10.5993. Min Act: -0.1700
Data Index: 723808 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19