Model: None
Dataset: The Pile
Neuron 2870 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 8.3914. Min Range: -8.3914
Max Act: 8.3914. Min Act: -0.1700
Data Index: 337432 (The Pile)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3914. Min Range: -8.3914
Max Act: 8.2039. Min Act: -0.1700
Data Index: 6373788 (The Pile)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3914. Min Range: -8.3914
Max Act: 8.0164. Min Act: -0.1700
Data Index: 136646 (The Pile)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3914. Min Range: -8.3914
Max Act: 7.9852. Min Act: -0.1700
Data Index: 6868956 (The Pile)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3914. Min Range: -8.3914
Max Act: 7.8289. Min Act: -0.1700
Data Index: 8741679 (The Pile)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3914. Min Range: -8.3914
Max Act: 7.8289. Min Act: -0.1700
Data Index: 4119829 (The Pile)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3914. Min Range: -8.3914
Max Act: 7.7977. Min Act: -0.1700
Data Index: 8134069 (The Pile)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3914. Min Range: -8.3914
Max Act: 7.7977. Min Act: -0.1700
Data Index: 1747230 (The Pile)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3914. Min Range: -8.3914
Max Act: 7.7977. Min Act: -0.1700
Data Index: 8768990 (The Pile)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3914. Min Range: -8.3914
Max Act: 7.7664. Min Act: -0.1699
Data Index: 4153901 (The Pile)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3914. Min Range: -8.3914
Max Act: 7.7664. Min Act: -0.1700
Data Index: 4122623 (The Pile)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3914. Min Range: -8.3914
Max Act: 7.7039. Min Act: -0.1700
Data Index: 7514966 (The Pile)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3914. Min Range: -8.3914
Max Act: 7.7039. Min Act: -0.1700
Data Index: 4469779 (The Pile)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3914. Min Range: -8.3914
Max Act: 7.6727. Min Act: -0.1700
Data Index: 5604815 (The Pile)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3914. Min Range: -8.3914
Max Act: 7.6727. Min Act: -0.1699
Data Index: 1744499 (The Pile)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3914. Min Range: -8.3914
Max Act: 7.6727. Min Act: -0.1700
Data Index: 10063931 (The Pile)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3914. Min Range: -8.3914
Max Act: 7.6727. Min Act: -0.1700
Data Index: 119469 (The Pile)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3914. Min Range: -8.3914
Max Act: 7.6414. Min Act: -0.1700
Data Index: 4365492 (The Pile)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3914. Min Range: -8.3914
Max Act: 7.6414. Min Act: -0.1700
Data Index: 7632808 (The Pile)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3914. Min Range: -8.3914
Max Act: 7.6414. Min Act: -0.1700
Data Index: 3633816 (The Pile)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19