Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3622 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2266. Min Range: -6.2266
Max Act: 6.2266. Min Act: -0.1700
Data Index: 3224956 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2266. Min Range: -6.2266
Max Act: 6.1641. Min Act: -0.1700
Data Index: 4500439 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2266. Min Range: -6.2266
Max Act: 6.0704. Min Act: -0.1700
Data Index: 6908992 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2266. Min Range: -6.2266
Max Act: 6.1016. Min Act: -0.1700
Data Index: 6912292 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2266. Min Range: -6.2266
Max Act: 6.0391. Min Act: -0.1700
Data Index: 5944497 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2266. Min Range: -6.2266
Max Act: 6.0391. Min Act: -0.1700
Data Index: 5157722 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2266. Min Range: -6.2266
Max Act: 6.0079. Min Act: -0.1700
Data Index: 6449005 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2266. Min Range: -6.2266
Max Act: 5.9766. Min Act: -0.1700
Data Index: 8642686 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2266. Min Range: -6.2266
Max Act: 5.9766. Min Act: -0.1700
Data Index: 4848108 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2266. Min Range: -6.2266
Max Act: 5.9454. Min Act: -0.1700
Data Index: 2518031 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2266. Min Range: -6.2266
Max Act: 5.9454. Min Act: -0.1700
Data Index: 4994402 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2266. Min Range: -6.2266
Max Act: 5.9454. Min Act: -0.1700
Data Index: 6449003 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2266. Min Range: -6.2266
Max Act: 5.9141. Min Act: -0.1700
Data Index: 78643 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2266. Min Range: -6.2266
Max Act: 5.9141. Min Act: -0.1700
Data Index: 3701928 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2266. Min Range: -6.2266
Max Act: 5.8829. Min Act: -0.1700
Data Index: 1941379 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2266. Min Range: -6.2266
Max Act: 5.8516. Min Act: -0.1700
Data Index: 1974329 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2266. Min Range: -6.2266
Max Act: 5.8516. Min Act: -0.1700
Data Index: 6050298 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2266. Min Range: -6.2266
Max Act: 5.8204. Min Act: -0.1700
Data Index: 1718874 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2266. Min Range: -6.2266
Max Act: 5.7891. Min Act: -0.1700
Data Index: 6620264 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2266. Min Range: -6.2266
Max Act: 5.8204. Min Act: -0.1700
Data Index: 5685326 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19