Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5540 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0252. Min Range: -10.0252
Max Act: 10.0252. Min Act: -0.1700
Data Index: 488769 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.7127. Min Act: -0.1700
Data Index: 8459497 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.5252. Min Act: -0.1700
Data Index: 5387944 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.4627. Min Act: -0.1700
Data Index: 6422412 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.4627. Min Act: -0.1700
Data Index: 4712514 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.1502. Min Act: -0.1700
Data Index: 2786405 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0252. Min Range: -10.0252
Max Act: 9.0252. Min Act: -0.1700
Data Index: 3349336 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0252. Min Range: -10.0252
Max Act: 8.9627. Min Act: -0.1700
Data Index: 8809553 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0252. Min Range: -10.0252
Max Act: 8.7752. Min Act: -0.1700
Data Index: 7524874 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0252. Min Range: -10.0252
Max Act: 8.7752. Min Act: -0.1700
Data Index: 2850757 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0252. Min Range: -10.0252
Max Act: 8.7752. Min Act: -0.1700
Data Index: 2974562 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0252. Min Range: -10.0252
Max Act: 8.7127. Min Act: -0.1700
Data Index: 3215521 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0252. Min Range: -10.0252
Max Act: 8.7752. Min Act: -0.1700
Data Index: 6040425 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0252. Min Range: -10.0252
Max Act: 8.6502. Min Act: -0.1700
Data Index: 6672406 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0252. Min Range: -10.0252
Max Act: 8.7127. Min Act: -0.1700
Data Index: 1701290 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0252. Min Range: -10.0252
Max Act: 8.6502. Min Act: -0.1700
Data Index: 7692431 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0252. Min Range: -10.0252
Max Act: 8.6502. Min Act: -0.1700
Data Index: 6467551 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0252. Min Range: -10.0252
Max Act: 8.6502. Min Act: -0.1700
Data Index: 6298786 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0252. Min Range: -10.0252
Max Act: 8.6502. Min Act: -0.1700
Data Index: 8061044 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0252. Min Range: -10.0252
Max Act: 8.6502. Min Act: -0.1700
Data Index: 7879947 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19