Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2153 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8779. Min Range: -3.8779
Max Act: 3.8779. Min Act: -0.1700
Data Index: 8808241 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8779. Min Range: -3.8779
Max Act: 3.8779. Min Act: -0.1700
Data Index: 8373606 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8779. Min Range: -3.8779
Max Act: 3.8779. Min Act: -0.1700
Data Index: 6627752 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8779. Min Range: -3.8779
Max Act: 3.8154. Min Act: -0.1700
Data Index: 3426236 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8779. Min Range: -3.8779
Max Act: 3.8467. Min Act: -0.1700
Data Index: 1197987 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8779. Min Range: -3.8779
Max Act: 3.7528. Min Act: -0.1700
Data Index: 1082076 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8779. Min Range: -3.8779
Max Act: 3.7841. Min Act: -0.1700
Data Index: 8494113 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8779. Min Range: -3.8779
Max Act: 3.7841. Min Act: -0.1700
Data Index: 3456759 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8779. Min Range: -3.8779
Max Act: 3.7841. Min Act: -0.1700
Data Index: 6715012 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8779. Min Range: -3.8779
Max Act: 3.7528. Min Act: -0.1700
Data Index: 1179309 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8779. Min Range: -3.8779
Max Act: 3.7216. Min Act: -0.1700
Data Index: 5661263 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8779. Min Range: -3.8779
Max Act: 3.7216. Min Act: -0.1700
Data Index: 4203675 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8779. Min Range: -3.8779
Max Act: 3.7528. Min Act: -0.1700
Data Index: 8498640 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8779. Min Range: -3.8779
Max Act: 3.7528. Min Act: -0.1700
Data Index: 8263787 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8779. Min Range: -3.8779
Max Act: 3.7216. Min Act: -0.1700
Data Index: 3480350 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8779. Min Range: -3.8779
Max Act: 3.7216. Min Act: -0.1700
Data Index: 3687957 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8779. Min Range: -3.8779
Max Act: 3.7528. Min Act: -0.1700
Data Index: 8617123 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8779. Min Range: -3.8779
Max Act: 3.7216. Min Act: -0.1700
Data Index: 3354245 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8779. Min Range: -3.8779
Max Act: 3.7528. Min Act: -0.1700
Data Index: 7989470 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8779. Min Range: -3.8779
Max Act: 3.6903. Min Act: -0.1700
Data Index: 8782962 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19