Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3042 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9303. Min Range: -7.9303
Max Act: 7.9303. Min Act: -0.1700
Data Index: 8618386 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9303. Min Range: -7.9303
Max Act: 7.9303. Min Act: -0.1700
Data Index: 8204894 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9303. Min Range: -7.9303
Max Act: 7.8366. Min Act: -0.1700
Data Index: 1982461 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9303. Min Range: -7.9303
Max Act: 7.8366. Min Act: -0.1700
Data Index: 3971649 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9303. Min Range: -7.9303
Max Act: 7.7428. Min Act: -0.1700
Data Index: 3430566 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9303. Min Range: -7.9303
Max Act: 7.7116. Min Act: -0.1700
Data Index: 6515368 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9303. Min Range: -7.9303
Max Act: 7.6178. Min Act: -0.1700
Data Index: 5624408 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9303. Min Range: -7.9303
Max Act: 7.6491. Min Act: -0.1700
Data Index: 140858 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9303. Min Range: -7.9303
Max Act: 7.6491. Min Act: -0.1700
Data Index: 7876039 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9303. Min Range: -7.9303
Max Act: 7.5553. Min Act: -0.1700
Data Index: 3648303 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9303. Min Range: -7.9303
Max Act: 7.5241. Min Act: -0.1700
Data Index: 3441836 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9303. Min Range: -7.9303
Max Act: 7.5241. Min Act: -0.1700
Data Index: 3781422 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9303. Min Range: -7.9303
Max Act: 7.4928. Min Act: -0.1700
Data Index: 1333912 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9303. Min Range: -7.9303
Max Act: 7.4928. Min Act: -0.1700
Data Index: 2273793 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9303. Min Range: -7.9303
Max Act: 7.5241. Min Act: -0.1700
Data Index: 2326504 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9303. Min Range: -7.9303
Max Act: 7.4616. Min Act: -0.1700
Data Index: 8094188 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9303. Min Range: -7.9303
Max Act: 7.4303. Min Act: -0.1700
Data Index: 7405058 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9303. Min Range: -7.9303
Max Act: 7.4928. Min Act: -0.1700
Data Index: 1888093 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9303. Min Range: -7.9303
Max Act: 7.4303. Min Act: -0.1700
Data Index: 4249393 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9303. Min Range: -7.9303
Max Act: 7.3991. Min Act: -0.1700
Data Index: 2686919 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19