Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2359 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3352. Min Range: -7.3352
Max Act: 7.3352. Min Act: -0.1700
Data Index: 1955453 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3352. Min Range: -7.3352
Max Act: 7.1790. Min Act: -0.1700
Data Index: 1214191 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3352. Min Range: -7.3352
Max Act: 7.0852. Min Act: -0.1700
Data Index: 3122741 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3352. Min Range: -7.3352
Max Act: 7.0540. Min Act: -0.1700
Data Index: 4372401 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3352. Min Range: -7.3352
Max Act: 7.0852. Min Act: -0.1700
Data Index: 7715477 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3352. Min Range: -7.3352
Max Act: 6.9602. Min Act: -0.1700
Data Index: 1974013 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3352. Min Range: -7.3352
Max Act: 6.9290. Min Act: -0.1700
Data Index: 7611589 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3352. Min Range: -7.3352
Max Act: 6.8665. Min Act: -0.1700
Data Index: 7914880 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3352. Min Range: -7.3352
Max Act: 6.8040. Min Act: -0.1700
Data Index: 1237708 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3352. Min Range: -7.3352
Max Act: 6.8040. Min Act: -0.1700
Data Index: 3701002 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3352. Min Range: -7.3352
Max Act: 6.7727. Min Act: -0.1700
Data Index: 329976 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3352. Min Range: -7.3352
Max Act: 6.7415. Min Act: -0.1700
Data Index: 1087391 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3352. Min Range: -7.3352
Max Act: 6.7415. Min Act: -0.1700
Data Index: 3836364 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3352. Min Range: -7.3352
Max Act: 6.7727. Min Act: -0.1700
Data Index: 8424459 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3352. Min Range: -7.3352
Max Act: 6.7102. Min Act: -0.1700
Data Index: 1173459 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3352. Min Range: -7.3352
Max Act: 6.7415. Min Act: -0.1700
Data Index: 6836648 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3352. Min Range: -7.3352
Max Act: 6.7102. Min Act: -0.1700
Data Index: 7955014 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3352. Min Range: -7.3352
Max Act: 6.6790. Min Act: -0.1700
Data Index: 925724 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3352. Min Range: -7.3352
Max Act: 6.6790. Min Act: -0.1700
Data Index: 8095212 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3352. Min Range: -7.3352
Max Act: 6.6790. Min Act: -0.1700
Data Index: 6491730 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19