Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1826 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8381. Min Range: -1.8381
Max Act: 1.8381. Min Act: -0.1700
Data Index: 5854583 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8381. Min Range: -1.8381
Max Act: 1.8381. Min Act: -0.1700
Data Index: 1908372 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8381. Min Range: -1.8381
Max Act: 1.7693. Min Act: -0.1700
Data Index: 3592368 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8381. Min Range: -1.8381
Max Act: 1.7520. Min Act: -0.1700
Data Index: 245030 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8381. Min Range: -1.8381
Max Act: 1.7347. Min Act: -0.1700
Data Index: 8818921 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8381. Min Range: -1.8381
Max Act: 1.7347. Min Act: -0.1700
Data Index: 5103732 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8381. Min Range: -1.8381
Max Act: 1.7347. Min Act: -0.1700
Data Index: 5558796 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8381. Min Range: -1.8381
Max Act: 1.7347. Min Act: -0.1700
Data Index: 8274149 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8381. Min Range: -1.8381
Max Act: 1.7347. Min Act: -0.1700
Data Index: 3398572 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8381. Min Range: -1.8381
Max Act: 1.7347. Min Act: -0.1700
Data Index: 8291101 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8381. Min Range: -1.8381
Max Act: 1.7174. Min Act: -0.1700
Data Index: 6331949 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8381. Min Range: -1.8381
Max Act: 1.7174. Min Act: -0.1700
Data Index: 8818917 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8381. Min Range: -1.8381
Max Act: 1.7001. Min Act: -0.1700
Data Index: 8020333 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8381. Min Range: -1.8381
Max Act: 1.7001. Min Act: -0.1700
Data Index: 1326006 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8381. Min Range: -1.8381
Max Act: 1.7001. Min Act: -0.1700
Data Index: 1449679 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8381. Min Range: -1.8381
Max Act: 1.6827. Min Act: -0.1700
Data Index: 2619430 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8381. Min Range: -1.8381
Max Act: 1.6827. Min Act: -0.1700
Data Index: 3062535 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8381. Min Range: -1.8381
Max Act: 1.6827. Min Act: -0.1700
Data Index: 5005678 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8381. Min Range: -1.8381
Max Act: 1.6654. Min Act: -0.1700
Data Index: 361473 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8381. Min Range: -1.8381
Max Act: 1.6654. Min Act: -0.1700
Data Index: 3962256 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19