Model: None
Dataset: The Pile
Neuron 1435 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 4.6995. Min Range: -4.6995
Max Act: 4.6995. Min Act: -0.1700
Data Index: 1817010 (The Pile)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6995. Min Range: -4.6995
Max Act: 4.6370. Min Act: -0.1700
Data Index: 9943948 (The Pile)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6995. Min Range: -4.6995
Max Act: 4.5745. Min Act: -0.1700
Data Index: 2653 (The Pile)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6995. Min Range: -4.6995
Max Act: 4.5745. Min Act: -0.1700
Data Index: 4667201 (The Pile)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6995. Min Range: -4.6995
Max Act: 4.5745. Min Act: -0.1700
Data Index: 5262789 (The Pile)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6995. Min Range: -4.6995
Max Act: 4.5745. Min Act: -0.1700
Data Index: 9918069 (The Pile)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6995. Min Range: -4.6995
Max Act: 4.5745. Min Act: -0.1700
Data Index: 1367137 (The Pile)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6995. Min Range: -4.6995
Max Act: 4.5432. Min Act: -0.1700
Data Index: 734098 (The Pile)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6995. Min Range: -4.6995
Max Act: 4.5432. Min Act: -0.1700
Data Index: 3901715 (The Pile)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6995. Min Range: -4.6995
Max Act: 4.5120. Min Act: -0.1700
Data Index: 80268 (The Pile)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6995. Min Range: -4.6995
Max Act: 4.4807. Min Act: -0.1700
Data Index: 2144576 (The Pile)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6995. Min Range: -4.6995
Max Act: 4.4495. Min Act: -0.1700
Data Index: 4035188 (The Pile)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6995. Min Range: -4.6995
Max Act: 4.4495. Min Act: -0.1700
Data Index: 1959366 (The Pile)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6995. Min Range: -4.6995
Max Act: 4.4495. Min Act: -0.1700
Data Index: 5449659 (The Pile)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6995. Min Range: -4.6995
Max Act: 4.4495. Min Act: -0.1700
Data Index: 6668068 (The Pile)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6995. Min Range: -4.6995
Max Act: 4.4495. Min Act: -0.1700
Data Index: 2130123 (The Pile)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6995. Min Range: -4.6995
Max Act: 4.4495. Min Act: -0.1700
Data Index: 10541844 (The Pile)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6995. Min Range: -4.6995
Max Act: 4.4182. Min Act: -0.1700
Data Index: 6389245 (The Pile)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6995. Min Range: -4.6995
Max Act: 4.4182. Min Act: -0.1700
Data Index: 9902570 (The Pile)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6995. Min Range: -4.6995
Max Act: 4.4182. Min Act: -0.1700
Data Index: 7606973 (The Pile)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #19