Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3924 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3446. Min Range: -5.3446
Max Act: 5.3446. Min Act: -0.1700
Data Index: 5679096 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3446. Min Range: -5.3446
Max Act: 5.2821. Min Act: -0.1700
Data Index: 1773433 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3446. Min Range: -5.3446
Max Act: 5.1258. Min Act: -0.1700
Data Index: 7147943 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3446. Min Range: -5.3446
Max Act: 5.0633. Min Act: -0.1700
Data Index: 86231 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3446. Min Range: -5.3446
Max Act: 5.0321. Min Act: -0.1700
Data Index: 6737439 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3446. Min Range: -5.3446
Max Act: 5.0633. Min Act: -0.1700
Data Index: 3746502 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3446. Min Range: -5.3446
Max Act: 5.0008. Min Act: -0.1700
Data Index: 2608502 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3446. Min Range: -5.3446
Max Act: 5.0008. Min Act: -0.1700
Data Index: 4104695 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3446. Min Range: -5.3446
Max Act: 5.0008. Min Act: -0.1700
Data Index: 4993857 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3446. Min Range: -5.3446
Max Act: 5.0008. Min Act: -0.1700
Data Index: 4834192 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3446. Min Range: -5.3446
Max Act: 5.0008. Min Act: -0.1700
Data Index: 388732 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3446. Min Range: -5.3446
Max Act: 5.0008. Min Act: -0.1700
Data Index: 3522868 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3446. Min Range: -5.3446
Max Act: 5.0321. Min Act: -0.1700
Data Index: 1726597 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3446. Min Range: -5.3446
Max Act: 4.9696. Min Act: -0.1700
Data Index: 4250732 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3446. Min Range: -5.3446
Max Act: 4.9696. Min Act: -0.1700
Data Index: 8518634 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3446. Min Range: -5.3446
Max Act: 4.9696. Min Act: -0.1700
Data Index: 7035996 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3446. Min Range: -5.3446
Max Act: 4.9696. Min Act: -0.1700
Data Index: 6187017 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3446. Min Range: -5.3446
Max Act: 4.9383. Min Act: -0.1700
Data Index: 784882 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3446. Min Range: -5.3446
Max Act: 4.9071. Min Act: -0.1700
Data Index: 4783450 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3446. Min Range: -5.3446
Max Act: 4.9383. Min Act: -0.1700
Data Index: 2716180 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19