Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 371 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3722. Min Range: -10.3722
Max Act: 10.3722. Min Act: -0.1700
Data Index: 3602233 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3722. Min Range: -10.3722
Max Act: 10.3722. Min Act: -0.1700
Data Index: 8624961 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3722. Min Range: -10.3722
Max Act: 10.3722. Min Act: -0.1700
Data Index: 5075204 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3722. Min Range: -10.3722
Max Act: 10.2472. Min Act: -0.1700
Data Index: 1700495 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3722. Min Range: -10.3722
Max Act: 10.2472. Min Act: -0.1700
Data Index: 91999 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3722. Min Range: -10.3722
Max Act: 10.2472. Min Act: -0.1700
Data Index: 8361954 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3722. Min Range: -10.3722
Max Act: 10.1222. Min Act: -0.1700
Data Index: 1545105 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3722. Min Range: -10.3722
Max Act: 10.1222. Min Act: -0.1700
Data Index: 2259767 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3722. Min Range: -10.3722
Max Act: 10.0597. Min Act: -0.1700
Data Index: 6628723 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3722. Min Range: -10.3722
Max Act: 10.1222. Min Act: -0.1700
Data Index: 3322286 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3722. Min Range: -10.3722
Max Act: 10.0597. Min Act: -0.1700
Data Index: 867649 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3722. Min Range: -10.3722
Max Act: 10.0597. Min Act: -0.1700
Data Index: 5097714 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3722. Min Range: -10.3722
Max Act: 10.0597. Min Act: -0.1700
Data Index: 765516 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3722. Min Range: -10.3722
Max Act: 9.9972. Min Act: -0.1700
Data Index: 8203 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3722. Min Range: -10.3722
Max Act: 9.9972. Min Act: -0.1700
Data Index: 795690 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3722. Min Range: -10.3722
Max Act: 9.9347. Min Act: -0.1700
Data Index: 4680382 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3722. Min Range: -10.3722
Max Act: 9.9347. Min Act: -0.1700
Data Index: 3733692 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3722. Min Range: -10.3722
Max Act: 9.9347. Min Act: -0.1700
Data Index: 8037493 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3722. Min Range: -10.3722
Max Act: 9.9347. Min Act: -0.1700
Data Index: 94055 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3722. Min Range: -10.3722
Max Act: 9.9347. Min Act: -0.1700
Data Index: 3357276 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19