Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4965 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.6779. Min Act: -0.1700
Data Index: 1297605 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.6779. Min Act: -0.1700
Data Index: 1617352 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.6154. Min Act: -0.1700
Data Index: 7604549 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.5842. Min Act: -0.1700
Data Index: 3366645 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.5842. Min Act: -0.1700
Data Index: 4784121 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.5217. Min Act: -0.1700
Data Index: 5604823 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.4904. Min Act: -0.1700
Data Index: 8679524 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.5217. Min Act: -0.1700
Data Index: 5167460 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.5217. Min Act: -0.1700
Data Index: 6069579 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.4592. Min Act: -0.1700
Data Index: 8786382 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.4592. Min Act: -0.1700
Data Index: 7360831 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.4279. Min Act: -0.1700
Data Index: 1040644 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.4592. Min Act: -0.1700
Data Index: 2108922 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.4279. Min Act: -0.1700
Data Index: 6048121 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.4279. Min Act: -0.1700
Data Index: 8001191 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.4279. Min Act: -0.1700
Data Index: 4432764 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.3967. Min Act: -0.1700
Data Index: 5017780 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.4279. Min Act: -0.1700
Data Index: 4533289 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.3967. Min Act: -0.1700
Data Index: 3017504 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6779. Min Range: -4.6779
Max Act: 4.3967. Min Act: -0.1700
Data Index: 1202225 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19