Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1722 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.8834. Min Range: -10.8834
Max Act: 10.8834. Min Act: -0.1700
Data Index: 535396 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8834. Min Range: -10.8834
Max Act: 10.2584. Min Act: -0.1700
Data Index: 8502034 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8834. Min Range: -10.8834
Max Act: 10.1334. Min Act: -0.1700
Data Index: 5987961 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8834. Min Range: -10.8834
Max Act: 9.7584. Min Act: -0.1700
Data Index: 6727604 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8834. Min Range: -10.8834
Max Act: 9.6959. Min Act: -0.1700
Data Index: 1059183 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8834. Min Range: -10.8834
Max Act: 9.6959. Min Act: -0.1700
Data Index: 1007140 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8834. Min Range: -10.8834
Max Act: 9.6334. Min Act: -0.1700
Data Index: 3167353 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8834. Min Range: -10.8834
Max Act: 9.6959. Min Act: -0.1700
Data Index: 5831590 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8834. Min Range: -10.8834
Max Act: 9.6334. Min Act: -0.1700
Data Index: 1379793 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8834. Min Range: -10.8834
Max Act: 9.6334. Min Act: -0.1700
Data Index: 1059182 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8834. Min Range: -10.8834
Max Act: 9.5709. Min Act: -0.1700
Data Index: 5716674 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8834. Min Range: -10.8834
Max Act: 9.6334. Min Act: -0.1700
Data Index: 2657194 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8834. Min Range: -10.8834
Max Act: 9.5709. Min Act: -0.1700
Data Index: 564227 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8834. Min Range: -10.8834
Max Act: 9.5084. Min Act: -0.1700
Data Index: 8440698 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8834. Min Range: -10.8834
Max Act: 9.4459. Min Act: -0.1700
Data Index: 15419 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8834. Min Range: -10.8834
Max Act: 9.3834. Min Act: -0.1700
Data Index: 2560251 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8834. Min Range: -10.8834
Max Act: 9.3834. Min Act: -0.1700
Data Index: 5953866 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8834. Min Range: -10.8834
Max Act: 9.3209. Min Act: -0.1700
Data Index: 7659385 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8834. Min Range: -10.8834
Max Act: 9.3834. Min Act: -0.1700
Data Index: 2577452 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8834. Min Range: -10.8834
Max Act: 9.3209. Min Act: -0.1700
Data Index: 355805 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19