Model: None
Dataset: The Pile
Neuron 3071 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 2.7433. Min Range: -2.7433
Max Act: 2.7433. Min Act: -0.1699
Data Index: 8287570 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7433. Min Range: -2.7433
Max Act: 2.7433. Min Act: -0.1700
Data Index: 2730442 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7433. Min Range: -2.7433
Max Act: 2.7273. Min Act: -0.1699
Data Index: 9256921 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7433. Min Range: -2.7433
Max Act: 2.7273. Min Act: -0.1700
Data Index: 6198435 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7433. Min Range: -2.7433
Max Act: 2.7113. Min Act: -0.1699
Data Index: 2460448 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7433. Min Range: -2.7433
Max Act: 2.7113. Min Act: -0.1700
Data Index: 725210 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7433. Min Range: -2.7433
Max Act: 2.6953. Min Act: -0.1700
Data Index: 2060577 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7433. Min Range: -2.7433
Max Act: 2.6953. Min Act: -0.1700
Data Index: 6279536 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7433. Min Range: -2.7433
Max Act: 2.6793. Min Act: -0.1699
Data Index: 5655010 (The Pile)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7433. Min Range: -2.7433
Max Act: 2.6793. Min Act: -0.1700
Data Index: 10750247 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7433. Min Range: -2.7433
Max Act: 2.6793. Min Act: -0.1700
Data Index: 9278673 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7433. Min Range: -2.7433
Max Act: 2.6793. Min Act: -0.1700
Data Index: 6022948 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7433. Min Range: -2.7433
Max Act: 2.6633. Min Act: -0.1700
Data Index: 1287035 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7433. Min Range: -2.7433
Max Act: 2.6633. Min Act: -0.1700
Data Index: 4681606 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7433. Min Range: -2.7433
Max Act: 2.6633. Min Act: -0.1700
Data Index: 5974616 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7433. Min Range: -2.7433
Max Act: 2.6633. Min Act: -0.1700
Data Index: 3610727 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7433. Min Range: -2.7433
Max Act: 2.6633. Min Act: -0.1700
Data Index: 3382677 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7433. Min Range: -2.7433
Max Act: 2.6633. Min Act: -0.1700
Data Index: 3779854 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7433. Min Range: -2.7433
Max Act: 2.6633. Min Act: -0.1699
Data Index: 4409534 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7433. Min Range: -2.7433
Max Act: 2.6472. Min Act: -0.1699
Data Index: 6973108 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19