Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3728 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5415. Min Range: -6.5415
Max Act: 6.5415. Min Act: -0.1700
Data Index: 7942190 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5415. Min Range: -6.5415
Max Act: 6.4477. Min Act: -0.1700
Data Index: 6166678 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5415. Min Range: -6.5415
Max Act: 6.4477. Min Act: -0.1700
Data Index: 1822015 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5415. Min Range: -6.5415
Max Act: 6.3852. Min Act: -0.1700
Data Index: 303093 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5415. Min Range: -6.5415
Max Act: 6.3852. Min Act: -0.1700
Data Index: 8587918 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5415. Min Range: -6.5415
Max Act: 6.3540. Min Act: -0.1700
Data Index: 998129 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5415. Min Range: -6.5415
Max Act: 6.2290. Min Act: -0.1700
Data Index: 3608928 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5415. Min Range: -6.5415
Max Act: 6.1977. Min Act: -0.1700
Data Index: 3442458 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5415. Min Range: -6.5415
Max Act: 6.1665. Min Act: -0.1700
Data Index: 1458663 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5415. Min Range: -6.5415
Max Act: 6.1665. Min Act: -0.1700
Data Index: 8421211 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5415. Min Range: -6.5415
Max Act: 6.1352. Min Act: -0.1700
Data Index: 6944162 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5415. Min Range: -6.5415
Max Act: 6.1352. Min Act: -0.1700
Data Index: 5210954 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5415. Min Range: -6.5415
Max Act: 6.1352. Min Act: -0.1700
Data Index: 3065523 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5415. Min Range: -6.5415
Max Act: 6.1352. Min Act: -0.1700
Data Index: 6404846 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5415. Min Range: -6.5415
Max Act: 6.1352. Min Act: -0.1700
Data Index: 6329228 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5415. Min Range: -6.5415
Max Act: 6.1040. Min Act: -0.1700
Data Index: 6992342 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5415. Min Range: -6.5415
Max Act: 6.1040. Min Act: -0.1700
Data Index: 7322190 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5415. Min Range: -6.5415
Max Act: 6.0727. Min Act: -0.1700
Data Index: 4533140 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5415. Min Range: -6.5415
Max Act: 6.0727. Min Act: -0.1700
Data Index: 2997370 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5415. Min Range: -6.5415
Max Act: 6.0415. Min Act: -0.1700
Data Index: 514989 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19