Model: None
Dataset: The Pile
Neuron 321 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.8270. Min Range: -2.8270
Max Act: 2.8270. Min Act: -0.1700
Data Index: 1988955 (The Pile)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8270. Min Range: -2.8270
Max Act: 2.7792. Min Act: -0.1700
Data Index: 5580524 (The Pile)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8270. Min Range: -2.8270
Max Act: 2.7313. Min Act: -0.1700
Data Index: 6496095 (The Pile)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8270. Min Range: -2.8270
Max Act: 2.6993. Min Act: -0.1700
Data Index: 10330845 (The Pile)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8270. Min Range: -2.8270
Max Act: 2.6993. Min Act: -0.1700
Data Index: 996951 (The Pile)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8270. Min Range: -2.8270
Max Act: 2.6833. Min Act: -0.1700
Data Index: 1380393 (The Pile)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8270. Min Range: -2.8270
Max Act: 2.7153. Min Act: -0.1700
Data Index: 3383220 (The Pile)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8270. Min Range: -2.8270
Max Act: 2.6833. Min Act: -0.1700
Data Index: 3698478 (The Pile)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8270. Min Range: -2.8270
Max Act: 2.6993. Min Act: -0.1700
Data Index: 5369869 (The Pile)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8270. Min Range: -2.8270
Max Act: 2.6993. Min Act: -0.1700
Data Index: 1313165 (The Pile)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8270. Min Range: -2.8270
Max Act: 2.6673. Min Act: -0.1700
Data Index: 8782322 (The Pile)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8270. Min Range: -2.8270
Max Act: 2.6352. Min Act: -0.1700
Data Index: 10233941 (The Pile)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8270. Min Range: -2.8270
Max Act: 2.6513. Min Act: -0.1700
Data Index: 9317682 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8270. Min Range: -2.8270
Max Act: 2.6673. Min Act: -0.1700
Data Index: 3237968 (The Pile)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8270. Min Range: -2.8270
Max Act: 2.6673. Min Act: -0.1700
Data Index: 6905665 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8270. Min Range: -2.8270
Max Act: 2.6673. Min Act: -0.1700
Data Index: 8465828 (The Pile)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8270. Min Range: -2.8270
Max Act: 2.6513. Min Act: -0.1700
Data Index: 5174069 (The Pile)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8270. Min Range: -2.8270
Max Act: 2.6513. Min Act: -0.1700
Data Index: 5899267 (The Pile)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8270. Min Range: -2.8270
Max Act: 2.6513. Min Act: -0.1700
Data Index: 7966613 (The Pile)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8270. Min Range: -2.8270
Max Act: 2.6352. Min Act: -0.1700
Data Index: 4743106 (The Pile)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19