Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3431 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9376. Min Range: -6.9376
Max Act: 6.9376. Min Act: -0.1700
Data Index: 1233431 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9376. Min Range: -6.9376
Max Act: 6.8751. Min Act: -0.1700
Data Index: 8378850 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9376. Min Range: -6.9376
Max Act: 6.8438. Min Act: -0.1700
Data Index: 5694147 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9376. Min Range: -6.9376
Max Act: 6.7501. Min Act: -0.1700
Data Index: 4565422 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9376. Min Range: -6.9376
Max Act: 6.7501. Min Act: -0.1700
Data Index: 5441776 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9376. Min Range: -6.9376
Max Act: 6.6876. Min Act: -0.1700
Data Index: 6920566 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9376. Min Range: -6.9376
Max Act: 6.7501. Min Act: -0.1700
Data Index: 5383691 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9376. Min Range: -6.9376
Max Act: 6.6563. Min Act: -0.1700
Data Index: 5226081 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9376. Min Range: -6.9376
Max Act: 6.5626. Min Act: -0.1700
Data Index: 1387071 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9376. Min Range: -6.9376
Max Act: 6.5313. Min Act: -0.1700
Data Index: 1192649 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9376. Min Range: -6.9376
Max Act: 6.5626. Min Act: -0.1700
Data Index: 4579915 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9376. Min Range: -6.9376
Max Act: 6.4688. Min Act: -0.1700
Data Index: 550038 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9376. Min Range: -6.9376
Max Act: 6.4688. Min Act: -0.1700
Data Index: 5285703 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9376. Min Range: -6.9376
Max Act: 6.4688. Min Act: -0.1700
Data Index: 5368828 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9376. Min Range: -6.9376
Max Act: 6.4376. Min Act: -0.1700
Data Index: 2441098 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9376. Min Range: -6.9376
Max Act: 6.4376. Min Act: -0.1700
Data Index: 2761024 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9376. Min Range: -6.9376
Max Act: 6.4063. Min Act: -0.1700
Data Index: 5929650 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9376. Min Range: -6.9376
Max Act: 6.4063. Min Act: -0.1700
Data Index: 1485903 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9376. Min Range: -6.9376
Max Act: 6.4376. Min Act: -0.1700
Data Index: 3408595 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9376. Min Range: -6.9376
Max Act: 6.4063. Min Act: -0.1700
Data Index: 3220954 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19