Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 744 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1709. Min Range: -8.1709
Max Act: 8.1709. Min Act: -0.1700
Data Index: 5530646 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1709. Min Range: -8.1709
Max Act: 8.1084. Min Act: -0.1700
Data Index: 907938 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1709. Min Range: -8.1709
Max Act: 7.7959. Min Act: -0.1700
Data Index: 1655902 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1709. Min Range: -8.1709
Max Act: 7.7959. Min Act: -0.1700
Data Index: 6181320 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1709. Min Range: -8.1709
Max Act: 7.7334. Min Act: -0.1700
Data Index: 2723555 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1709. Min Range: -8.1709
Max Act: 7.7334. Min Act: -0.1700
Data Index: 3946779 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1709. Min Range: -8.1709
Max Act: 7.6709. Min Act: -0.1700
Data Index: 1510317 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1709. Min Range: -8.1709
Max Act: 7.6084. Min Act: -0.1700
Data Index: 456978 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1709. Min Range: -8.1709
Max Act: 7.6709. Min Act: -0.1700
Data Index: 1621556 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1709. Min Range: -8.1709
Max Act: 7.6084. Min Act: -0.1700
Data Index: 34995 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1709. Min Range: -8.1709
Max Act: 7.6084. Min Act: -0.1700
Data Index: 4352270 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1709. Min Range: -8.1709
Max Act: 7.4834. Min Act: -0.1700
Data Index: 8500750 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1709. Min Range: -8.1709
Max Act: 7.4834. Min Act: -0.1700
Data Index: 6977873 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1709. Min Range: -8.1709
Max Act: 7.4521. Min Act: -0.1700
Data Index: 738537 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1709. Min Range: -8.1709
Max Act: 7.4209. Min Act: -0.1700
Data Index: 6790397 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1709. Min Range: -8.1709
Max Act: 7.4209. Min Act: -0.1700
Data Index: 4403057 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1709. Min Range: -8.1709
Max Act: 7.4209. Min Act: -0.1700
Data Index: 1639155 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1709. Min Range: -8.1709
Max Act: 7.4209. Min Act: -0.1700
Data Index: 3487305 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1709. Min Range: -8.1709
Max Act: 7.4209. Min Act: -0.1700
Data Index: 901997 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1709. Min Range: -8.1709
Max Act: 7.3896. Min Act: -0.1700
Data Index: 940990 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19