Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2865 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0259. Min Range: -6.0259
Max Act: 6.0259. Min Act: -0.1700
Data Index: 4066106 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0259. Min Range: -6.0259
Max Act: 6.0259. Min Act: -0.1700
Data Index: 7556312 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0259. Min Range: -6.0259
Max Act: 5.9321. Min Act: -0.1700
Data Index: 1206675 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0259. Min Range: -6.0259
Max Act: 5.9009. Min Act: -0.1700
Data Index: 7341032 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0259. Min Range: -6.0259
Max Act: 5.9009. Min Act: -0.1700
Data Index: 7408000 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0259. Min Range: -6.0259
Max Act: 5.8384. Min Act: -0.1700
Data Index: 4539318 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0259. Min Range: -6.0259
Max Act: 5.8384. Min Act: -0.1700
Data Index: 7719483 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0259. Min Range: -6.0259
Max Act: 5.7759. Min Act: -0.1700
Data Index: 3786197 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0259. Min Range: -6.0259
Max Act: 5.7759. Min Act: -0.1700
Data Index: 1960686 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0259. Min Range: -6.0259
Max Act: 5.7759. Min Act: -0.1700
Data Index: 8736447 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0259. Min Range: -6.0259
Max Act: 5.8071. Min Act: -0.1700
Data Index: 7487641 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0259. Min Range: -6.0259
Max Act: 5.7759. Min Act: -0.1700
Data Index: 1235623 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0259. Min Range: -6.0259
Max Act: 5.7446. Min Act: -0.1700
Data Index: 8333252 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0259. Min Range: -6.0259
Max Act: 5.7134. Min Act: -0.1700
Data Index: 6460606 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0259. Min Range: -6.0259
Max Act: 5.7134. Min Act: -0.1700
Data Index: 1093833 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0259. Min Range: -6.0259
Max Act: 5.6821. Min Act: -0.1700
Data Index: 8452810 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0259. Min Range: -6.0259
Max Act: 5.6821. Min Act: -0.1700
Data Index: 6617663 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0259. Min Range: -6.0259
Max Act: 5.6821. Min Act: -0.1700
Data Index: 707691 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0259. Min Range: -6.0259
Max Act: 5.6509. Min Act: -0.1700
Data Index: 931897 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0259. Min Range: -6.0259
Max Act: 5.6196. Min Act: -0.1700
Data Index: 1239885 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19