Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2555. Min Range: -5.2555
Max Act: 5.2555. Min Act: -0.1700
Data Index: 3948093 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2555. Min Range: -5.2555
Max Act: 5.1305. Min Act: -0.1700
Data Index: 1826523 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2555. Min Range: -5.2555
Max Act: 4.9743. Min Act: -0.1700
Data Index: 6671067 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2555. Min Range: -5.2555
Max Act: 4.9430. Min Act: -0.1700
Data Index: 8299980 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2555. Min Range: -5.2555
Max Act: 4.8805. Min Act: -0.1699
Data Index: 7018831 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2555. Min Range: -5.2555
Max Act: 4.8805. Min Act: -0.1700
Data Index: 1441659 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2555. Min Range: -5.2555
Max Act: 4.8493. Min Act: -0.1700
Data Index: 7075838 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2555. Min Range: -5.2555
Max Act: 4.8493. Min Act: -0.1700
Data Index: 8624735 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2555. Min Range: -5.2555
Max Act: 4.8180. Min Act: -0.1700
Data Index: 5743545 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2555. Min Range: -5.2555
Max Act: 4.7868. Min Act: -0.1700
Data Index: 7203435 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2555. Min Range: -5.2555
Max Act: 4.7868. Min Act: -0.1700
Data Index: 8299994 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2555. Min Range: -5.2555
Max Act: 4.7555. Min Act: -0.1700
Data Index: 5802946 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2555. Min Range: -5.2555
Max Act: 4.7243. Min Act: -0.1700
Data Index: 8497653 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2555. Min Range: -5.2555
Max Act: 4.7555. Min Act: -0.1700
Data Index: 8178017 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2555. Min Range: -5.2555
Max Act: 4.7243. Min Act: -0.1700
Data Index: 47558 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2555. Min Range: -5.2555
Max Act: 4.7555. Min Act: -0.1700
Data Index: 4916437 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2555. Min Range: -5.2555
Max Act: 4.7243. Min Act: -0.1700
Data Index: 1494957 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2555. Min Range: -5.2555
Max Act: 4.7243. Min Act: -0.1700
Data Index: 2766900 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2555. Min Range: -5.2555
Max Act: 4.7243. Min Act: -0.1700
Data Index: 5324730 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2555. Min Range: -5.2555
Max Act: 4.7243. Min Act: -0.1700
Data Index: 3167858 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #19