Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 421 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6223. Min Range: -6.6223
Max Act: 6.6223. Min Act: -0.1700
Data Index: 8025716 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6223. Min Range: -6.6223
Max Act: 6.6223. Min Act: -0.1700
Data Index: 5053329 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6223. Min Range: -6.6223
Max Act: 6.6223. Min Act: -0.1700
Data Index: 4803995 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6223. Min Range: -6.6223
Max Act: 6.5910. Min Act: -0.1700
Data Index: 3520428 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6223. Min Range: -6.6223
Max Act: 6.4348. Min Act: -0.1700
Data Index: 6175322 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6223. Min Range: -6.6223
Max Act: 6.4348. Min Act: -0.1700
Data Index: 2662073 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6223. Min Range: -6.6223
Max Act: 6.4348. Min Act: -0.1700
Data Index: 2408475 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6223. Min Range: -6.6223
Max Act: 6.3723. Min Act: -0.1700
Data Index: 7301612 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6223. Min Range: -6.6223
Max Act: 6.3410. Min Act: -0.1700
Data Index: 2367243 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6223. Min Range: -6.6223
Max Act: 6.3098. Min Act: -0.1700
Data Index: 2759734 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6223. Min Range: -6.6223
Max Act: 6.3410. Min Act: -0.1700
Data Index: 4858811 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6223. Min Range: -6.6223
Max Act: 6.2785. Min Act: -0.1700
Data Index: 4576991 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6223. Min Range: -6.6223
Max Act: 6.2785. Min Act: -0.1700
Data Index: 7459805 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6223. Min Range: -6.6223
Max Act: 6.2473. Min Act: -0.1700
Data Index: 1527296 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6223. Min Range: -6.6223
Max Act: 6.2160. Min Act: -0.1700
Data Index: 98953 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6223. Min Range: -6.6223
Max Act: 6.2160. Min Act: -0.1700
Data Index: 1640327 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6223. Min Range: -6.6223
Max Act: 6.1848. Min Act: -0.1700
Data Index: 2776546 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6223. Min Range: -6.6223
Max Act: 6.1848. Min Act: -0.1700
Data Index: 2202964 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6223. Min Range: -6.6223
Max Act: 6.1848. Min Act: -0.1700
Data Index: 7712636 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6223. Min Range: -6.6223
Max Act: 6.1848. Min Act: -0.1700
Data Index: 4696968 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #19