Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1869 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.7131. Min Act: -0.1700
Data Index: 2407177 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.6193. Min Act: -0.1700
Data Index: 7917731 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.5568. Min Act: -0.1700
Data Index: 2407176 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.4006. Min Act: -0.1700
Data Index: 1821667 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.3693. Min Act: -0.1700
Data Index: 6921558 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.3381. Min Act: -0.1700
Data Index: 5764433 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.2443. Min Act: -0.1700
Data Index: 5691278 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.2443. Min Act: -0.1700
Data Index: 4087425 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.2131. Min Act: -0.1700
Data Index: 684406 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.2131. Min Act: -0.1700
Data Index: 5840571 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1818. Min Act: -0.1700
Data Index: 3169915 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1818. Min Act: -0.1700
Data Index: 8636287 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1818. Min Act: -0.1700
Data Index: 7064814 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1506. Min Act: -0.1700
Data Index: 736131 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.0881. Min Act: -0.1700
Data Index: 595865 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1506. Min Act: -0.1700
Data Index: 6190651 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1193. Min Act: -0.1700
Data Index: 2515172 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1193. Min Act: -0.1700
Data Index: 2799565 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.1193. Min Act: -0.1700
Data Index: 938611 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7131. Min Range: -7.7131
Max Act: 7.0881. Min Act: -0.1700
Data Index: 869242 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19