Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3736 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.9108. Min Range: -12.9108
Max Act: 12.9108. Min Act: -0.1700
Data Index: 1977740 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.9108. Min Range: -12.9108
Max Act: 12.9108. Min Act: -0.1697
Data Index: 512581 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.9108. Min Range: -12.9108
Max Act: 12.7233. Min Act: -0.1700
Data Index: 7063549 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.9108. Min Range: -12.9108
Max Act: 12.5983. Min Act: -0.1700
Data Index: 366805 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.9108. Min Range: -12.9108
Max Act: 12.5983. Min Act: -0.1693
Data Index: 7636416 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.9108. Min Range: -12.9108
Max Act: 12.5358. Min Act: -0.1699
Data Index: 323936 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.9108. Min Range: -12.9108
Max Act: 12.5358. Min Act: -0.1686
Data Index: 2772691 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.9108. Min Range: -12.9108
Max Act: 12.5358. Min Act: -0.1692
Data Index: 2380946 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.9108. Min Range: -12.9108
Max Act: 12.4733. Min Act: -0.1698
Data Index: 7806418 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.9108. Min Range: -12.9108
Max Act: 12.4733. Min Act: -0.1699
Data Index: 5455068 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.9108. Min Range: -12.9108
Max Act: 12.5358. Min Act: -0.1700
Data Index: 6863719 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.9108. Min Range: -12.9108
Max Act: 12.4733. Min Act: -0.1700
Data Index: 3684607 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.9108. Min Range: -12.9108
Max Act: 12.4733. Min Act: -0.1700
Data Index: 7303253 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.9108. Min Range: -12.9108
Max Act: 12.5358. Min Act: -0.1700
Data Index: 6631840 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.9108. Min Range: -12.9108
Max Act: 12.5358. Min Act: -0.1699
Data Index: 4082911 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.9108. Min Range: -12.9108
Max Act: 12.4733. Min Act: -0.1699
Data Index: 376879 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.9108. Min Range: -12.9108
Max Act: 12.4108. Min Act: -0.1700
Data Index: 6942846 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.9108. Min Range: -12.9108
Max Act: 12.4733. Min Act: -0.1700
Data Index: 629240 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.9108. Min Range: -12.9108
Max Act: 12.4108. Min Act: -0.1700
Data Index: 7513837 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.9108. Min Range: -12.9108
Max Act: 12.3483. Min Act: -0.1693
Data Index: 5153145 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19