Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1158 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.0833. Min Range: -0.0833
Max Act: 0.0833. Min Act: -0.0002
Data Index: 1010 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0833. Min Range: -0.0833
Max Act: 0.0833. Min Act: -0.0002
Data Index: 2502 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0833. Min Range: -0.0833
Max Act: 0.0833. Min Act: -0.0002
Data Index: 476 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0833. Min Range: -0.0833
Max Act: 0.0833. Min Act: -0.0002
Data Index: 1461 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0833. Min Range: -0.0833
Max Act: 0.0833. Min Act: -0.0002
Data Index: 443 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0833. Min Range: -0.0833
Max Act: 0.0833. Min Act: -0.0002
Data Index: 1897 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0833. Min Range: -0.0833
Max Act: 0.0833. Min Act: -0.0002
Data Index: 1694 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0833. Min Range: -0.0833
Max Act: 0.0833. Min Act: -0.0002
Data Index: 1227 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0833. Min Range: -0.0833
Max Act: 0.0833. Min Act: -0.0002
Data Index: 1960 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0833. Min Range: -0.0833
Max Act: 0.0833. Min Act: -0.0002
Data Index: 2430 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0833. Min Range: -0.0833
Max Act: 0.0833. Min Act: -0.0002
Data Index: 1631 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0833. Min Range: -0.0833
Max Act: 0.0833. Min Act: -0.0002
Data Index: 1961 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0833. Min Range: -0.0833
Max Act: 0.0833. Min Act: -0.0002
Data Index: 2135 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0833. Min Range: -0.0833
Max Act: 0.0833. Min Act: -0.0002
Data Index: 893 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0833. Min Range: -0.0833
Max Act: 0.0833. Min Act: -0.0002
Data Index: 2112 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0833. Min Range: -0.0833
Max Act: 0.0833. Min Act: -0.0002
Data Index: 2002 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0833. Min Range: -0.0833
Max Act: 0.0833. Min Act: -0.0002
Data Index: 1375 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0833. Min Range: -0.0833
Max Act: 0.0833. Min Act: -0.0002
Data Index: 660 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0833. Min Range: -0.0833
Max Act: 0.0833. Min Act: -0.0002
Data Index: 252 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0833. Min Range: -0.0833
Max Act: 0.0833. Min Act: -0.0002
Data Index: 653 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19