Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7242. Min Range: -7.7242
Max Act: 7.7242. Min Act: -0.1700
Data Index: 7851535 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7242. Min Range: -7.7242
Max Act: 7.7242. Min Act: -0.1700
Data Index: 3898599 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7242. Min Range: -7.7242
Max Act: 7.7242. Min Act: -0.1700
Data Index: 4018243 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7242. Min Range: -7.7242
Max Act: 7.6305. Min Act: -0.1700
Data Index: 2522654 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7242. Min Range: -7.7242
Max Act: 7.5680. Min Act: -0.1700
Data Index: 2161898 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7242. Min Range: -7.7242
Max Act: 7.5055. Min Act: -0.1700
Data Index: 1914542 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7242. Min Range: -7.7242
Max Act: 7.5055. Min Act: -0.1700
Data Index: 7171275 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7242. Min Range: -7.7242
Max Act: 7.4742. Min Act: -0.1700
Data Index: 838525 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7242. Min Range: -7.7242
Max Act: 7.4430. Min Act: -0.1700
Data Index: 8476207 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7242. Min Range: -7.7242
Max Act: 7.4117. Min Act: -0.1700
Data Index: 7154506 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7242. Min Range: -7.7242
Max Act: 7.3805. Min Act: -0.1700
Data Index: 3766317 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7242. Min Range: -7.7242
Max Act: 7.3805. Min Act: -0.1700
Data Index: 4754929 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7242. Min Range: -7.7242
Max Act: 7.3805. Min Act: -0.1700
Data Index: 8731058 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7242. Min Range: -7.7242
Max Act: 7.3180. Min Act: -0.1700
Data Index: 6564347 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7242. Min Range: -7.7242
Max Act: 7.3492. Min Act: -0.1700
Data Index: 8159921 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7242. Min Range: -7.7242
Max Act: 7.3492. Min Act: -0.1700
Data Index: 3958068 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7242. Min Range: -7.7242
Max Act: 7.3180. Min Act: -0.1700
Data Index: 3945047 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7242. Min Range: -7.7242
Max Act: 7.3180. Min Act: -0.1700
Data Index: 1341252 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7242. Min Range: -7.7242
Max Act: 7.3180. Min Act: -0.1700
Data Index: 773026 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7242. Min Range: -7.7242
Max Act: 7.3180. Min Act: -0.1700
Data Index: 8267770 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19