Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4102 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9926. Min Range: -10.9926
Max Act: 10.9926. Min Act: -0.1700
Data Index: 5536771 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9926. Min Range: -10.9926
Max Act: 10.1801. Min Act: -0.1700
Data Index: 2855977 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9926. Min Range: -10.9926
Max Act: 9.7426. Min Act: -0.1700
Data Index: 1594916 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9926. Min Range: -10.9926
Max Act: 9.6801. Min Act: -0.1700
Data Index: 4659363 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9926. Min Range: -10.9926
Max Act: 9.6801. Min Act: -0.1700
Data Index: 889527 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9926. Min Range: -10.9926
Max Act: 9.6176. Min Act: -0.1700
Data Index: 4360809 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9926. Min Range: -10.9926
Max Act: 9.6176. Min Act: -0.1700
Data Index: 8740896 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9926. Min Range: -10.9926
Max Act: 9.4926. Min Act: -0.1700
Data Index: 5238509 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9926. Min Range: -10.9926
Max Act: 9.3676. Min Act: -0.1700
Data Index: 7511724 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9926. Min Range: -10.9926
Max Act: 9.3676. Min Act: -0.1700
Data Index: 243747 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9926. Min Range: -10.9926
Max Act: 9.3676. Min Act: -0.1700
Data Index: 4622087 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9926. Min Range: -10.9926
Max Act: 9.3676. Min Act: -0.1700
Data Index: 6535243 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9926. Min Range: -10.9926
Max Act: 9.3051. Min Act: -0.1700
Data Index: 7611526 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9926. Min Range: -10.9926
Max Act: 9.3051. Min Act: -0.1700
Data Index: 6509843 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9926. Min Range: -10.9926
Max Act: 9.2426. Min Act: -0.1700
Data Index: 3943721 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9926. Min Range: -10.9926
Max Act: 9.2426. Min Act: -0.1700
Data Index: 1872952 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9926. Min Range: -10.9926
Max Act: 9.1801. Min Act: -0.1700
Data Index: 6716688 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9926. Min Range: -10.9926
Max Act: 9.1801. Min Act: -0.1700
Data Index: 5524839 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9926. Min Range: -10.9926
Max Act: 9.1801. Min Act: -0.1700
Data Index: 8592101 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9926. Min Range: -10.9926
Max Act: 9.1801. Min Act: -0.1700
Data Index: 4140093 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #19