Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1719 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1844. Min Range: -11.1844
Max Act: 11.1844. Min Act: -0.1700
Data Index: 1561118 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.9344. Min Act: -0.1700
Data Index: 6293183 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.9969. Min Act: -0.1700
Data Index: 2898552 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.9344. Min Act: -0.1700
Data Index: 2561744 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.9344. Min Act: -0.1700
Data Index: 7549053 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.8094. Min Act: -0.1700
Data Index: 1269547 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.8719. Min Act: -0.1700
Data Index: 4741817 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.8094. Min Act: -0.1700
Data Index: 655898 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.7469. Min Act: -0.1700
Data Index: 3521404 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.6844. Min Act: -0.1700
Data Index: 4114402 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.7469. Min Act: -0.1700
Data Index: 7019291 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.7469. Min Act: -0.1700
Data Index: 7308085 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.6844. Min Act: -0.1700
Data Index: 7993962 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.6844. Min Act: -0.1700
Data Index: 4382659 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.6844. Min Act: -0.1700
Data Index: 4565508 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.6219. Min Act: -0.1700
Data Index: 7474620 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.6219. Min Act: -0.1700
Data Index: 4885741 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.6219. Min Act: -0.1700
Data Index: 5414008 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.6219. Min Act: -0.1698
Data Index: 7917893 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1844. Min Range: -11.1844
Max Act: 10.6219. Min Act: -0.1700
Data Index: 5592083 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19