Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3555 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5973. Min Range: -7.5973
Max Act: 7.5973. Min Act: -0.1700
Data Index: 6907476 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5973. Min Range: -7.5973
Max Act: 7.4410. Min Act: -0.1700
Data Index: 7909230 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5973. Min Range: -7.5973
Max Act: 7.4410. Min Act: -0.1700
Data Index: 4223199 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5973. Min Range: -7.5973
Max Act: 7.3473. Min Act: -0.1700
Data Index: 3032199 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5973. Min Range: -7.5973
Max Act: 7.2848. Min Act: -0.1700
Data Index: 5276896 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5973. Min Range: -7.5973
Max Act: 7.3160. Min Act: -0.1700
Data Index: 5614607 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5973. Min Range: -7.5973
Max Act: 7.2848. Min Act: -0.1700
Data Index: 232892 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5973. Min Range: -7.5973
Max Act: 7.2535. Min Act: -0.1700
Data Index: 7483431 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5973. Min Range: -7.5973
Max Act: 7.2223. Min Act: -0.1700
Data Index: 3328647 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5973. Min Range: -7.5973
Max Act: 7.2223. Min Act: -0.1700
Data Index: 480360 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5973. Min Range: -7.5973
Max Act: 7.2223. Min Act: -0.1700
Data Index: 34711 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5973. Min Range: -7.5973
Max Act: 7.1910. Min Act: -0.1700
Data Index: 744805 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5973. Min Range: -7.5973
Max Act: 7.1598. Min Act: -0.1700
Data Index: 7400426 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5973. Min Range: -7.5973
Max Act: 7.1910. Min Act: -0.1700
Data Index: 1793292 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5973. Min Range: -7.5973
Max Act: 7.1598. Min Act: -0.1700
Data Index: 2876502 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5973. Min Range: -7.5973
Max Act: 7.1598. Min Act: -0.1700
Data Index: 6585555 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5973. Min Range: -7.5973
Max Act: 7.1598. Min Act: -0.1700
Data Index: 1166617 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5973. Min Range: -7.5973
Max Act: 7.1598. Min Act: -0.1700
Data Index: 6307307 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5973. Min Range: -7.5973
Max Act: 7.1285. Min Act: -0.1700
Data Index: 767625 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5973. Min Range: -7.5973
Max Act: 7.1285. Min Act: -0.1700
Data Index: 5815799 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #19