Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1096 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.1527. Min Range: -12.1527
Max Act: 12.1527. Min Act: -0.1700
Data Index: 196479 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.1527. Min Range: -12.1527
Max Act: 11.9652. Min Act: -0.1700
Data Index: 3413979 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.1527. Min Range: -12.1527
Max Act: 11.9027. Min Act: -0.1700
Data Index: 62364 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.1527. Min Range: -12.1527
Max Act: 11.9027. Min Act: -0.1700
Data Index: 583698 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.1527. Min Range: -12.1527
Max Act: 11.8402. Min Act: -0.1700
Data Index: 3413981 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.1527. Min Range: -12.1527
Max Act: 11.7777. Min Act: -0.1700
Data Index: 3413984 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.1527. Min Range: -12.1527
Max Act: 11.7152. Min Act: -0.1700
Data Index: 3298556 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.1527. Min Range: -12.1527
Max Act: 11.6527. Min Act: -0.1700
Data Index: 3413974 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.1527. Min Range: -12.1527
Max Act: 11.6527. Min Act: -0.1700
Data Index: 4463804 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.1527. Min Range: -12.1527
Max Act: 11.5902. Min Act: -0.1700
Data Index: 6835386 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.1527. Min Range: -12.1527
Max Act: 11.5277. Min Act: -0.1700
Data Index: 4382209 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.1527. Min Range: -12.1527
Max Act: 11.5277. Min Act: -0.1700
Data Index: 4480999 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.1527. Min Range: -12.1527
Max Act: 11.5277. Min Act: -0.1700
Data Index: 3413976 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.1527. Min Range: -12.1527
Max Act: 11.5277. Min Act: -0.1700
Data Index: 1118842 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.1527. Min Range: -12.1527
Max Act: 11.4652. Min Act: -0.1700
Data Index: 4495812 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.1527. Min Range: -12.1527
Max Act: 11.4652. Min Act: -0.1700
Data Index: 4052879 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.1527. Min Range: -12.1527
Max Act: 11.4652. Min Act: -0.1700
Data Index: 2903844 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.1527. Min Range: -12.1527
Max Act: 11.5277. Min Act: -0.1700
Data Index: 8111022 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.1527. Min Range: -12.1527
Max Act: 11.4027. Min Act: -0.1700
Data Index: 5826018 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.1527. Min Range: -12.1527
Max Act: 11.4027. Min Act: -0.1700
Data Index: 1914063 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19