Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5771 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.5905. Min Act: -0.1700
Data Index: 7600374 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.5592. Min Act: -0.1700
Data Index: 5667639 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.5122. Min Act: -0.1700
Data Index: 1059766 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.5122. Min Act: -0.1700
Data Index: 8796566 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.4809. Min Act: -0.1700
Data Index: 4839990 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.4809. Min Act: -0.1700
Data Index: 5525916 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.4652. Min Act: -0.1700
Data Index: 7665281 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.4652. Min Act: -0.1700
Data Index: 249646 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.4496. Min Act: -0.1700
Data Index: 6306293 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.4339. Min Act: -0.1700
Data Index: 1343278 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.4339. Min Act: -0.1700
Data Index: 127987 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.4182. Min Act: -0.1700
Data Index: 2324837 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.4025. Min Act: -0.1700
Data Index: 6606482 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.3869. Min Act: -0.1700
Data Index: 688652 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.3869. Min Act: -0.1700
Data Index: 4916551 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.3712. Min Act: -0.1700
Data Index: 3584041 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.3712. Min Act: -0.1700
Data Index: 599750 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.3398. Min Act: -0.1700
Data Index: 3065720 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.3712. Min Act: -0.1700
Data Index: 6218384 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5905. Min Range: -3.5905
Max Act: 3.3712. Min Act: -0.1700
Data Index: 5956274 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19