Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1476 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6128. Min Range: -7.6128
Max Act: 7.6128. Min Act: -0.1700
Data Index: 1881432 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6128. Min Range: -7.6128
Max Act: 7.3628. Min Act: -0.1700
Data Index: 8037564 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6128. Min Range: -7.6128
Max Act: 7.3316. Min Act: -0.1700
Data Index: 4467296 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6128. Min Range: -7.6128
Max Act: 7.2378. Min Act: -0.1700
Data Index: 977790 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6128. Min Range: -7.6128
Max Act: 7.1441. Min Act: -0.1700
Data Index: 6185254 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6128. Min Range: -7.6128
Max Act: 7.1128. Min Act: -0.1700
Data Index: 8374708 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6128. Min Range: -7.6128
Max Act: 7.0816. Min Act: -0.1700
Data Index: 7879930 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6128. Min Range: -7.6128
Max Act: 6.9566. Min Act: -0.1700
Data Index: 1579563 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6128. Min Range: -7.6128
Max Act: 6.9253. Min Act: -0.1700
Data Index: 7179684 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6128. Min Range: -7.6128
Max Act: 6.9253. Min Act: -0.1700
Data Index: 368464 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6128. Min Range: -7.6128
Max Act: 6.8628. Min Act: -0.1700
Data Index: 1375415 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6128. Min Range: -7.6128
Max Act: 6.8941. Min Act: -0.1700
Data Index: 4504658 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6128. Min Range: -7.6128
Max Act: 6.9253. Min Act: -0.1700
Data Index: 4864587 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6128. Min Range: -7.6128
Max Act: 6.8941. Min Act: -0.1700
Data Index: 617694 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6128. Min Range: -7.6128
Max Act: 6.8628. Min Act: -0.1700
Data Index: 4849505 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6128. Min Range: -7.6128
Max Act: 6.8628. Min Act: -0.1700
Data Index: 7617382 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6128. Min Range: -7.6128
Max Act: 6.8628. Min Act: -0.1700
Data Index: 3025210 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6128. Min Range: -7.6128
Max Act: 6.8316. Min Act: -0.1700
Data Index: 366443 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6128. Min Range: -7.6128
Max Act: 6.8316. Min Act: -0.1700
Data Index: 3891076 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6128. Min Range: -7.6128
Max Act: 6.8316. Min Act: -0.1700
Data Index: 3839678 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19