Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 570 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7843. Min Range: -4.7843
Max Act: 4.7843. Min Act: -0.1700
Data Index: 8715181 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7843. Min Range: -4.7843
Max Act: 4.7530. Min Act: -0.1700
Data Index: 5287981 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7843. Min Range: -4.7843
Max Act: 4.6905. Min Act: -0.1700
Data Index: 2722675 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7843. Min Range: -4.7843
Max Act: 4.6905. Min Act: -0.1700
Data Index: 7667403 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7843. Min Range: -4.7843
Max Act: 4.6905. Min Act: -0.1700
Data Index: 3604984 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7843. Min Range: -4.7843
Max Act: 4.6593. Min Act: -0.1700
Data Index: 7668121 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7843. Min Range: -4.7843
Max Act: 4.5968. Min Act: -0.1700
Data Index: 5113551 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7843. Min Range: -4.7843
Max Act: 4.5968. Min Act: -0.1700
Data Index: 5966884 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7843. Min Range: -4.7843
Max Act: 4.5968. Min Act: -0.1700
Data Index: 7667404 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7843. Min Range: -4.7843
Max Act: 4.5655. Min Act: -0.1700
Data Index: 4961772 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7843. Min Range: -4.7843
Max Act: 4.5343. Min Act: -0.1700
Data Index: 5678400 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7843. Min Range: -4.7843
Max Act: 4.5655. Min Act: -0.1700
Data Index: 7667405 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7843. Min Range: -4.7843
Max Act: 4.5655. Min Act: -0.1700
Data Index: 330408 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7843. Min Range: -4.7843
Max Act: 4.5343. Min Act: -0.1700
Data Index: 39127 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7843. Min Range: -4.7843
Max Act: 4.5343. Min Act: -0.1700
Data Index: 4322861 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7843. Min Range: -4.7843
Max Act: 4.5030. Min Act: -0.1700
Data Index: 4040078 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7843. Min Range: -4.7843
Max Act: 4.5030. Min Act: -0.1700
Data Index: 7005745 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7843. Min Range: -4.7843
Max Act: 4.4718. Min Act: -0.1700
Data Index: 1005370 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7843. Min Range: -4.7843
Max Act: 4.4718. Min Act: -0.1700
Data Index: 4986288 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7843. Min Range: -4.7843
Max Act: 4.4718. Min Act: -0.1700
Data Index: 3395994 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #19