Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4058 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8779. Min Range: -5.8779
Max Act: 5.8779. Min Act: -0.1700
Data Index: 1314317 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8779. Min Range: -5.8779
Max Act: 5.7529. Min Act: -0.1700
Data Index: 1521900 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8779. Min Range: -5.8779
Max Act: 5.7529. Min Act: -0.1700
Data Index: 5549776 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8779. Min Range: -5.8779
Max Act: 5.7216. Min Act: -0.1700
Data Index: 4985712 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8779. Min Range: -5.8779
Max Act: 5.6904. Min Act: -0.1700
Data Index: 5695032 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8779. Min Range: -5.8779
Max Act: 5.6279. Min Act: -0.1700
Data Index: 595500 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8779. Min Range: -5.8779
Max Act: 5.6591. Min Act: -0.1700
Data Index: 8522325 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8779. Min Range: -5.8779
Max Act: 5.6591. Min Act: -0.1700
Data Index: 7195922 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8779. Min Range: -5.8779
Max Act: 5.6591. Min Act: -0.1700
Data Index: 3740366 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8779. Min Range: -5.8779
Max Act: 5.6279. Min Act: -0.1700
Data Index: 735765 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8779. Min Range: -5.8779
Max Act: 5.6279. Min Act: -0.1700
Data Index: 7055736 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8779. Min Range: -5.8779
Max Act: 5.6591. Min Act: -0.1700
Data Index: 3005535 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8779. Min Range: -5.8779
Max Act: 5.6279. Min Act: -0.1700
Data Index: 4777601 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8779. Min Range: -5.8779
Max Act: 5.6279. Min Act: -0.1700
Data Index: 3155967 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8779. Min Range: -5.8779
Max Act: 5.5654. Min Act: -0.1700
Data Index: 7542029 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8779. Min Range: -5.8779
Max Act: 5.5654. Min Act: -0.1700
Data Index: 1521902 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8779. Min Range: -5.8779
Max Act: 5.5654. Min Act: -0.1700
Data Index: 1848797 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8779. Min Range: -5.8779
Max Act: 5.5654. Min Act: -0.1700
Data Index: 230290 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8779. Min Range: -5.8779
Max Act: 5.5654. Min Act: -0.1700
Data Index: 165492 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8779. Min Range: -5.8779
Max Act: 5.5654. Min Act: -0.1700
Data Index: 7516736 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #19