Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3496 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4973. Min Range: -6.4973
Max Act: 6.4973. Min Act: -0.1700
Data Index: 3262484 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4973. Min Range: -6.4973
Max Act: 6.4660. Min Act: -0.1700
Data Index: 4018779 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4973. Min Range: -6.4973
Max Act: 6.4035. Min Act: -0.1700
Data Index: 6898810 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4973. Min Range: -6.4973
Max Act: 6.3723. Min Act: -0.1700
Data Index: 2815627 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4973. Min Range: -6.4973
Max Act: 6.3723. Min Act: -0.1700
Data Index: 4161915 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4973. Min Range: -6.4973
Max Act: 6.3410. Min Act: -0.1700
Data Index: 50010 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4973. Min Range: -6.4973
Max Act: 6.3098. Min Act: -0.1700
Data Index: 4465163 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4973. Min Range: -6.4973
Max Act: 6.2785. Min Act: -0.1700
Data Index: 8518418 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4973. Min Range: -6.4973
Max Act: 6.2785. Min Act: -0.1700
Data Index: 5285760 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4973. Min Range: -6.4973
Max Act: 6.1848. Min Act: -0.1700
Data Index: 833929 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4973. Min Range: -6.4973
Max Act: 6.1848. Min Act: -0.1700
Data Index: 6767664 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4973. Min Range: -6.4973
Max Act: 6.1848. Min Act: -0.1700
Data Index: 3623100 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4973. Min Range: -6.4973
Max Act: 6.1535. Min Act: -0.1700
Data Index: 4789954 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4973. Min Range: -6.4973
Max Act: 6.1535. Min Act: -0.1700
Data Index: 4689733 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4973. Min Range: -6.4973
Max Act: 6.1223. Min Act: -0.1700
Data Index: 3326533 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4973. Min Range: -6.4973
Max Act: 6.1223. Min Act: -0.1700
Data Index: 3491875 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4973. Min Range: -6.4973
Max Act: 6.1223. Min Act: -0.1700
Data Index: 3868058 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4973. Min Range: -6.4973
Max Act: 6.0910. Min Act: -0.1700
Data Index: 192361 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4973. Min Range: -6.4973
Max Act: 6.0910. Min Act: -0.1700
Data Index: 6300086 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4973. Min Range: -6.4973
Max Act: 6.1223. Min Act: -0.1700
Data Index: 1628550 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #19