Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2785 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3134. Min Range: -7.3134
Max Act: 7.3134. Min Act: -0.1700
Data Index: 7806725 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3134. Min Range: -7.3134
Max Act: 7.1572. Min Act: -0.1700
Data Index: 4943506 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3134. Min Range: -7.3134
Max Act: 7.1572. Min Act: -0.1700
Data Index: 5620611 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3134. Min Range: -7.3134
Max Act: 7.0947. Min Act: -0.1700
Data Index: 435211 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3134. Min Range: -7.3134
Max Act: 7.0009. Min Act: -0.1700
Data Index: 7725008 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3134. Min Range: -7.3134
Max Act: 6.9384. Min Act: -0.1700
Data Index: 347712 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3134. Min Range: -7.3134
Max Act: 6.9697. Min Act: -0.1700
Data Index: 4762564 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3134. Min Range: -7.3134
Max Act: 6.9384. Min Act: -0.1700
Data Index: 305850 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3134. Min Range: -7.3134
Max Act: 6.8759. Min Act: -0.1700
Data Index: 7730379 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3134. Min Range: -7.3134
Max Act: 6.9384. Min Act: -0.1700
Data Index: 8114780 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3134. Min Range: -7.3134
Max Act: 6.8759. Min Act: -0.1700
Data Index: 4628563 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3134. Min Range: -7.3134
Max Act: 6.8447. Min Act: -0.1700
Data Index: 7492866 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3134. Min Range: -7.3134
Max Act: 6.8447. Min Act: -0.1700
Data Index: 525698 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3134. Min Range: -7.3134
Max Act: 6.8447. Min Act: -0.1700
Data Index: 2043806 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3134. Min Range: -7.3134
Max Act: 6.8447. Min Act: -0.1700
Data Index: 4945365 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3134. Min Range: -7.3134
Max Act: 6.8134. Min Act: -0.1700
Data Index: 7293489 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3134. Min Range: -7.3134
Max Act: 6.8134. Min Act: -0.1700
Data Index: 6527990 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3134. Min Range: -7.3134
Max Act: 6.8447. Min Act: -0.1700
Data Index: 1826397 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3134. Min Range: -7.3134
Max Act: 6.8134. Min Act: -0.1700
Data Index: 875305 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3134. Min Range: -7.3134
Max Act: 6.7822. Min Act: -0.1700
Data Index: 3900733 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19