Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3732 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7262. Min Range: -1.7262
Max Act: 1.7262. Min Act: -0.1700
Data Index: 3183749 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7262. Min Range: -1.7262
Max Act: 1.7003. Min Act: -0.1700
Data Index: 7306773 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7262. Min Range: -1.7262
Max Act: 1.6916. Min Act: -0.1700
Data Index: 6710636 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7262. Min Range: -1.7262
Max Act: 1.6829. Min Act: -0.1700
Data Index: 4256125 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7262. Min Range: -1.7262
Max Act: 1.6829. Min Act: -0.1700
Data Index: 4510451 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7262. Min Range: -1.7262
Max Act: 1.6742. Min Act: -0.1700
Data Index: 1775769 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7262. Min Range: -1.7262
Max Act: 1.6568. Min Act: -0.1700
Data Index: 6978622 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7262. Min Range: -1.7262
Max Act: 1.6568. Min Act: -0.1700
Data Index: 3528334 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7262. Min Range: -1.7262
Max Act: 1.6481. Min Act: -0.1700
Data Index: 4888594 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7262. Min Range: -1.7262
Max Act: 1.6481. Min Act: -0.1700
Data Index: 8363687 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7262. Min Range: -1.7262
Max Act: 1.6307. Min Act: -0.1700
Data Index: 5760359 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7262. Min Range: -1.7262
Max Act: 1.6394. Min Act: -0.1700
Data Index: 4247179 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7262. Min Range: -1.7262
Max Act: 1.6394. Min Act: -0.1699
Data Index: 3146512 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7262. Min Range: -1.7262
Max Act: 1.6481. Min Act: -0.1700
Data Index: 3964604 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7262. Min Range: -1.7262
Max Act: 1.6307. Min Act: -0.1700
Data Index: 6512043 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7262. Min Range: -1.7262
Max Act: 1.6394. Min Act: -0.1700
Data Index: 718308 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7262. Min Range: -1.7262
Max Act: 1.6307. Min Act: -0.1700
Data Index: 7143399 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7262. Min Range: -1.7262
Max Act: 1.6307. Min Act: -0.1700
Data Index: 3284953 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7262. Min Range: -1.7262
Max Act: 1.6220. Min Act: -0.1700
Data Index: 3789144 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7262. Min Range: -1.7262
Max Act: 1.6307. Min Act: -0.1700
Data Index: 6693157 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #19