Model: None
Dataset: The Pile
Neuron 2968 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')
Text #0
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.9722. Min Act: -0.1700
Data Index: 936715 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.9564. Min Act: -0.1700
Data Index: 10591150 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.9089. Min Act: -0.1700
Data Index: 5265208 (The Pile)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.8772. Min Act: -0.1700
Data Index: 6348760 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.8295. Min Act: -0.1700
Data Index: 6652436 (The Pile)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.8136. Min Act: -0.1700
Data Index: 10786017 (The Pile)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.8136. Min Act: -0.1700
Data Index: 3669252 (The Pile)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.7976. Min Act: -0.1700
Data Index: 3859106 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.7976. Min Act: -0.1700
Data Index: 3717526 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.7976. Min Act: -0.1700
Data Index: 2865326 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.7976. Min Act: -0.1700
Data Index: 60043 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.7976. Min Act: -0.1700
Data Index: 3686047 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.7976. Min Act: -0.1700
Data Index: 2382803 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.7976. Min Act: -0.1700
Data Index: 1276136 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.7976. Min Act: -0.1700
Data Index: 2251625 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.7976. Min Act: -0.1700
Data Index: 607065 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.7976. Min Act: -0.1700
Data Index: 1255114 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.7976. Min Act: -0.1700
Data Index: 2585724 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.7976. Min Act: -0.1700
Data Index: 934661 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9722. Min Range: -2.9722
Max Act: 2.7976. Min Act: -0.1700
Data Index: 326203 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19