Model: None
Dataset: The Pile
Neuron 1402 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.7590. Min Act: -0.1700
Data Index: 7917118 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.7434. Min Act: -0.1700
Data Index: 1229745 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6808. Min Act: -0.1700
Data Index: 4508898 (The Pile)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6651. Min Act: -0.1700
Data Index: 9142896 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6495. Min Act: -0.1700
Data Index: 8644901 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6338. Min Act: -0.1700
Data Index: 2233716 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6495. Min Act: -0.1700
Data Index: 4811118 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6182. Min Act: -0.1700
Data Index: 6459052 (The Pile)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6338. Min Act: -0.1700
Data Index: 10585834 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6182. Min Act: -0.1700
Data Index: 4553649 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6182. Min Act: -0.1700
Data Index: 9701816 (The Pile)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6025. Min Act: -0.1700
Data Index: 5230931 (The Pile)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6182. Min Act: -0.1700
Data Index: 1395912 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.6025. Min Act: -0.1700
Data Index: 9171057 (The Pile)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.5869. Min Act: -0.1700
Data Index: 7982810 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.5869. Min Act: -0.1700
Data Index: 2358704 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.5869. Min Act: -0.1700
Data Index: 8020421 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.5869. Min Act: -0.1700
Data Index: 4133458 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.5869. Min Act: -0.1700
Data Index: 5655837 (The Pile)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7590. Min Range: -3.7590
Max Act: 3.5869. Min Act: -0.1700
Data Index: 5708873 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19