Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3884 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5451. Min Range: -5.5451
Max Act: 5.5451. Min Act: -0.1700
Data Index: 3752279 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5451. Min Range: -5.5451
Max Act: 5.3263. Min Act: -0.1700
Data Index: 497722 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5451. Min Range: -5.5451
Max Act: 5.2326. Min Act: -0.1700
Data Index: 4589222 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5451. Min Range: -5.5451
Max Act: 5.2013. Min Act: -0.1700
Data Index: 3605430 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5451. Min Range: -5.5451
Max Act: 5.1701. Min Act: -0.1700
Data Index: 57999 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5451. Min Range: -5.5451
Max Act: 5.1701. Min Act: -0.1700
Data Index: 390945 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5451. Min Range: -5.5451
Max Act: 5.1388. Min Act: -0.1700
Data Index: 691523 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5451. Min Range: -5.5451
Max Act: 5.1388. Min Act: -0.1700
Data Index: 5397605 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5451. Min Range: -5.5451
Max Act: 5.1076. Min Act: -0.1700
Data Index: 6536146 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5451. Min Range: -5.5451
Max Act: 5.1076. Min Act: -0.1700
Data Index: 489373 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5451. Min Range: -5.5451
Max Act: 5.0763. Min Act: -0.1700
Data Index: 3610384 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5451. Min Range: -5.5451
Max Act: 5.0763. Min Act: -0.1700
Data Index: 8415114 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5451. Min Range: -5.5451
Max Act: 5.0763. Min Act: -0.1700
Data Index: 8816274 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5451. Min Range: -5.5451
Max Act: 5.0451. Min Act: -0.1700
Data Index: 1279709 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5451. Min Range: -5.5451
Max Act: 5.0763. Min Act: -0.1700
Data Index: 906873 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5451. Min Range: -5.5451
Max Act: 5.0451. Min Act: -0.1700
Data Index: 7432867 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5451. Min Range: -5.5451
Max Act: 5.0451. Min Act: -0.1700
Data Index: 6254927 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5451. Min Range: -5.5451
Max Act: 5.0138. Min Act: -0.1700
Data Index: 435940 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5451. Min Range: -5.5451
Max Act: 5.0138. Min Act: -0.1700
Data Index: 3631427 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5451. Min Range: -5.5451
Max Act: 5.0138. Min Act: -0.1700
Data Index: 2970092 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19