Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3935 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7178. Min Range: -4.7178
Max Act: 4.7178. Min Act: -0.1700
Data Index: 6479816 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7178. Min Range: -4.7178
Max Act: 4.7178. Min Act: -0.1700
Data Index: 7804369 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7178. Min Range: -4.7178
Max Act: 4.7178. Min Act: -0.1700
Data Index: 3256953 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7178. Min Range: -4.7178
Max Act: 4.6553. Min Act: -0.1700
Data Index: 8497462 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7178. Min Range: -4.7178
Max Act: 4.6553. Min Act: -0.1700
Data Index: 7534908 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7178. Min Range: -4.7178
Max Act: 4.6553. Min Act: -0.1700
Data Index: 7308471 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7178. Min Range: -4.7178
Max Act: 4.6553. Min Act: -0.1700
Data Index: 2766127 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7178. Min Range: -4.7178
Max Act: 4.6553. Min Act: -0.1700
Data Index: 3341762 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7178. Min Range: -4.7178
Max Act: 4.6553. Min Act: -0.1700
Data Index: 4861114 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7178. Min Range: -4.7178
Max Act: 4.6240. Min Act: -0.1700
Data Index: 7873760 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7178. Min Range: -4.7178
Max Act: 4.6240. Min Act: -0.1700
Data Index: 415393 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7178. Min Range: -4.7178
Max Act: 4.6240. Min Act: -0.1700
Data Index: 7112779 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7178. Min Range: -4.7178
Max Act: 4.5928. Min Act: -0.1700
Data Index: 4112952 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7178. Min Range: -4.7178
Max Act: 4.6240. Min Act: -0.1700
Data Index: 453522 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7178. Min Range: -4.7178
Max Act: 4.5928. Min Act: -0.1700
Data Index: 4160832 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7178. Min Range: -4.7178
Max Act: 4.5928. Min Act: -0.1700
Data Index: 5794835 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7178. Min Range: -4.7178
Max Act: 4.5615. Min Act: -0.1700
Data Index: 2048308 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7178. Min Range: -4.7178
Max Act: 4.5928. Min Act: -0.1700
Data Index: 1621270 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7178. Min Range: -4.7178
Max Act: 4.5928. Min Act: -0.1700
Data Index: 7058069 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7178. Min Range: -4.7178
Max Act: 4.5928. Min Act: -0.1700
Data Index: 3383033 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19