Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3276 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7509. Min Range: -6.7509
Max Act: 6.7509. Min Act: -0.1700
Data Index: 5591041 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7509. Min Range: -6.7509
Max Act: 6.3759. Min Act: -0.1700
Data Index: 6748580 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7509. Min Range: -6.7509
Max Act: 6.2822. Min Act: -0.1700
Data Index: 107086 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7509. Min Range: -6.7509
Max Act: 6.2509. Min Act: -0.1700
Data Index: 4094122 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7509. Min Range: -6.7509
Max Act: 6.2197. Min Act: -0.1700
Data Index: 8223617 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7509. Min Range: -6.7509
Max Act: 6.1884. Min Act: -0.1700
Data Index: 883055 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7509. Min Range: -6.7509
Max Act: 6.1572. Min Act: -0.1700
Data Index: 6870178 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7509. Min Range: -6.7509
Max Act: 6.1572. Min Act: -0.1700
Data Index: 8437677 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7509. Min Range: -6.7509
Max Act: 6.0947. Min Act: -0.1700
Data Index: 5871027 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7509. Min Range: -6.7509
Max Act: 6.0634. Min Act: -0.1700
Data Index: 1316686 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7509. Min Range: -6.7509
Max Act: 6.0634. Min Act: -0.1700
Data Index: 7297717 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7509. Min Range: -6.7509
Max Act: 6.0947. Min Act: -0.1700
Data Index: 508814 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7509. Min Range: -6.7509
Max Act: 6.0634. Min Act: -0.1700
Data Index: 6553822 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7509. Min Range: -6.7509
Max Act: 6.0634. Min Act: -0.1700
Data Index: 426215 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7509. Min Range: -6.7509
Max Act: 6.0322. Min Act: -0.1700
Data Index: 8564432 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7509. Min Range: -6.7509
Max Act: 6.0009. Min Act: -0.1700
Data Index: 2764454 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7509. Min Range: -6.7509
Max Act: 5.9697. Min Act: -0.1700
Data Index: 7131939 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7509. Min Range: -6.7509
Max Act: 5.9697. Min Act: -0.1700
Data Index: 2073221 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7509. Min Range: -6.7509
Max Act: 5.9697. Min Act: -0.1700
Data Index: 6465395 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7509. Min Range: -6.7509
Max Act: 5.9697. Min Act: -0.1700
Data Index: 5522857 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19