Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 14 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.6312. Min Range: -10.6312
Max Act: 10.6312. Min Act: -0.1700
Data Index: 446636 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.6312. Min Range: -10.6312
Max Act: 10.1937. Min Act: -0.1700
Data Index: 3998192 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.6312. Min Range: -10.6312
Max Act: 10.1312. Min Act: -0.1700
Data Index: 6323044 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.6312. Min Range: -10.6312
Max Act: 10.0687. Min Act: -0.1700
Data Index: 1446072 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.6312. Min Range: -10.6312
Max Act: 10.0062. Min Act: -0.1700
Data Index: 8405836 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.6312. Min Range: -10.6312
Max Act: 10.0062. Min Act: -0.1700
Data Index: 1446069 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.6312. Min Range: -10.6312
Max Act: 10.0062. Min Act: -0.1700
Data Index: 8810787 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.6312. Min Range: -10.6312
Max Act: 9.8812. Min Act: -0.1700
Data Index: 2814352 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.6312. Min Range: -10.6312
Max Act: 9.8812. Min Act: -0.1700
Data Index: 6609067 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.6312. Min Range: -10.6312
Max Act: 9.8812. Min Act: -0.1700
Data Index: 8731071 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.6312. Min Range: -10.6312
Max Act: 9.8812. Min Act: -0.1700
Data Index: 6192712 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.6312. Min Range: -10.6312
Max Act: 9.8187. Min Act: -0.1700
Data Index: 4629276 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.6312. Min Range: -10.6312
Max Act: 9.7562. Min Act: -0.1700
Data Index: 2610066 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.6312. Min Range: -10.6312
Max Act: 9.7562. Min Act: -0.1700
Data Index: 5568127 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.6312. Min Range: -10.6312
Max Act: 9.6937. Min Act: -0.1700
Data Index: 1416960 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.6312. Min Range: -10.6312
Max Act: 9.7562. Min Act: -0.1700
Data Index: 144127 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.6312. Min Range: -10.6312
Max Act: 9.7562. Min Act: -0.1700
Data Index: 1813360 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.6312. Min Range: -10.6312
Max Act: 9.6937. Min Act: -0.1700
Data Index: 6158488 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.6312. Min Range: -10.6312
Max Act: 9.6312. Min Act: -0.1700
Data Index: 189973 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.6312. Min Range: -10.6312
Max Act: 9.6937. Min Act: -0.1700
Data Index: 2856410 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19