Model: None
Dataset: The Pile
Neuron 2779 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.2442. Min Range: -3.2442
Max Act: 3.2442. Min Act: -0.1700
Data Index: 6039983 (The Pile)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2442. Min Range: -3.2442
Max Act: 3.2284. Min Act: -0.1700
Data Index: 1799166 (The Pile)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2442. Min Range: -3.2442
Max Act: 3.2284. Min Act: -0.1700
Data Index: 381211 (The Pile)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2442. Min Range: -3.2442
Max Act: 3.2284. Min Act: -0.1700
Data Index: 8525750 (The Pile)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2442. Min Range: -3.2442
Max Act: 3.2127. Min Act: -0.1700
Data Index: 8692289 (The Pile)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2442. Min Range: -3.2442
Max Act: 3.2127. Min Act: -0.1700
Data Index: 9637862 (The Pile)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2442. Min Range: -3.2442
Max Act: 3.2127. Min Act: -0.1700
Data Index: 8085393 (The Pile)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2442. Min Range: -3.2442
Max Act: 3.1970. Min Act: -0.1700
Data Index: 5164737 (The Pile)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2442. Min Range: -3.2442
Max Act: 3.1970. Min Act: -0.1700
Data Index: 4942437 (The Pile)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2442. Min Range: -3.2442
Max Act: 3.1812. Min Act: -0.1700
Data Index: 4651135 (The Pile)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2442. Min Range: -3.2442
Max Act: 3.1655. Min Act: -0.1700
Data Index: 909738 (The Pile)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2442. Min Range: -3.2442
Max Act: 3.1498. Min Act: -0.1700
Data Index: 8204784 (The Pile)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2442. Min Range: -3.2442
Max Act: 3.1498. Min Act: -0.1700
Data Index: 8867631 (The Pile)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2442. Min Range: -3.2442
Max Act: 3.1340. Min Act: -0.1700
Data Index: 4650127 (The Pile)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2442. Min Range: -3.2442
Max Act: 3.1340. Min Act: -0.1700
Data Index: 8226366 (The Pile)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2442. Min Range: -3.2442
Max Act: 3.1340. Min Act: -0.1700
Data Index: 7081465 (The Pile)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2442. Min Range: -3.2442
Max Act: 3.1182. Min Act: -0.1700
Data Index: 120730 (The Pile)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2442. Min Range: -3.2442
Max Act: 3.1182. Min Act: -0.1700
Data Index: 6346041 (The Pile)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2442. Min Range: -3.2442
Max Act: 3.1182. Min Act: -0.1700
Data Index: 7659924 (The Pile)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2442. Min Range: -3.2442
Max Act: 3.1025. Min Act: -0.1700
Data Index: 4013909 (The Pile)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19