Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4283 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8223. Min Range: -6.8223
Max Act: 6.8223. Min Act: -0.1700
Data Index: 742232 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8223. Min Range: -6.8223
Max Act: 6.6661. Min Act: -0.1700
Data Index: 317360 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8223. Min Range: -6.8223
Max Act: 6.4473. Min Act: -0.1700
Data Index: 6484920 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8223. Min Range: -6.8223
Max Act: 6.3848. Min Act: -0.1700
Data Index: 1700486 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8223. Min Range: -6.8223
Max Act: 6.3848. Min Act: -0.1700
Data Index: 7583368 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8223. Min Range: -6.8223
Max Act: 6.3536. Min Act: -0.1700
Data Index: 2765996 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8223. Min Range: -6.8223
Max Act: 6.2911. Min Act: -0.1700
Data Index: 1285976 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8223. Min Range: -6.8223
Max Act: 6.2598. Min Act: -0.1700
Data Index: 6827379 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8223. Min Range: -6.8223
Max Act: 6.2286. Min Act: -0.1700
Data Index: 8555501 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8223. Min Range: -6.8223
Max Act: 6.2286. Min Act: -0.1700
Data Index: 4267063 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8223. Min Range: -6.8223
Max Act: 6.2286. Min Act: -0.1700
Data Index: 106157 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8223. Min Range: -6.8223
Max Act: 6.1973. Min Act: -0.1700
Data Index: 3029634 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8223. Min Range: -6.8223
Max Act: 6.1661. Min Act: -0.1700
Data Index: 7062017 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8223. Min Range: -6.8223
Max Act: 6.1661. Min Act: -0.1700
Data Index: 4698505 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8223. Min Range: -6.8223
Max Act: 6.1661. Min Act: -0.1700
Data Index: 5460019 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8223. Min Range: -6.8223
Max Act: 6.1661. Min Act: -0.1700
Data Index: 869594 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8223. Min Range: -6.8223
Max Act: 6.1348. Min Act: -0.1700
Data Index: 3217160 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8223. Min Range: -6.8223
Max Act: 6.1348. Min Act: -0.1700
Data Index: 2397334 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8223. Min Range: -6.8223
Max Act: 6.1036. Min Act: -0.1700
Data Index: 5539507 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8223. Min Range: -6.8223
Max Act: 6.1036. Min Act: -0.1700
Data Index: 1299158 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19