Model: None
Dataset: The Pile
Neuron 2067 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 2.7340. Min Range: -2.7340
Max Act: 2.7340. Min Act: -0.1700
Data Index: 715574 (The Pile)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7340. Min Range: -2.7340
Max Act: 2.7180. Min Act: -0.1700
Data Index: 164830 (The Pile)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7340. Min Range: -2.7340
Max Act: 2.7020. Min Act: -0.1700
Data Index: 6673160 (The Pile)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7340. Min Range: -2.7340
Max Act: 2.7020. Min Act: -0.1700
Data Index: 2983198 (The Pile)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7340. Min Range: -2.7340
Max Act: 2.6700. Min Act: -0.1700
Data Index: 8722192 (The Pile)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7340. Min Range: -2.7340
Max Act: 2.6700. Min Act: -0.1700
Data Index: 10264557 (The Pile)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7340. Min Range: -2.7340
Max Act: 2.6539. Min Act: -0.1700
Data Index: 4611377 (The Pile)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7340. Min Range: -2.7340
Max Act: 2.6539. Min Act: -0.1700
Data Index: 6079197 (The Pile)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7340. Min Range: -2.7340
Max Act: 2.6539. Min Act: -0.1700
Data Index: 179146 (The Pile)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7340. Min Range: -2.7340
Max Act: 2.6539. Min Act: -0.1700
Data Index: 3543306 (The Pile)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7340. Min Range: -2.7340
Max Act: 2.6539. Min Act: -0.1700
Data Index: 6108127 (The Pile)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7340. Min Range: -2.7340
Max Act: 2.6379. Min Act: -0.1700
Data Index: 3980330 (The Pile)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7340. Min Range: -2.7340
Max Act: 2.6379. Min Act: -0.1700
Data Index: 4596356 (The Pile)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7340. Min Range: -2.7340
Max Act: 2.6379. Min Act: -0.1700
Data Index: 1492478 (The Pile)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7340. Min Range: -2.7340
Max Act: 2.6379. Min Act: -0.1700
Data Index: 1573144 (The Pile)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7340. Min Range: -2.7340
Max Act: 2.6379. Min Act: -0.1700
Data Index: 8429793 (The Pile)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7340. Min Range: -2.7340
Max Act: 2.6379. Min Act: -0.1700
Data Index: 5627520 (The Pile)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7340. Min Range: -2.7340
Max Act: 2.6218. Min Act: -0.1700
Data Index: 7599304 (The Pile)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7340. Min Range: -2.7340
Max Act: 2.6057. Min Act: -0.1700
Data Index: 9600854 (The Pile)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7340. Min Range: -2.7340
Max Act: 2.6057. Min Act: -0.1700
Data Index: 816607 (The Pile)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #19