Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 496 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.0951. Min Range: -0.0951
Max Act: 0.0951. Min Act: -0.0002
Data Index: 1987573 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0951. Min Range: -0.0951
Max Act: 0.0906. Min Act: -0.0002
Data Index: 1928155 (The Pile)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0951. Min Range: -0.0951
Max Act: 0.0927. Min Act: -0.0002
Data Index: 1767993 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0951. Min Range: -0.0951
Max Act: 0.0830. Min Act: -0.0002
Data Index: 1918944 (The Pile)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0951. Min Range: -0.0951
Max Act: 0.0891. Min Act: -0.0002
Data Index: 168305 (The Pile)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0951. Min Range: -0.0951
Max Act: 0.0653. Min Act: -0.0002
Data Index: 1407773 (The Pile)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0951. Min Range: -0.0951
Max Act: 0.0773. Min Act: -0.0002
Data Index: 1083963 (The Pile)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0951. Min Range: -0.0951
Max Act: 0.0610. Min Act: -0.0002
Data Index: 1032878 (The Pile)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0951. Min Range: -0.0951
Max Act: 0.0848. Min Act: -0.0002
Data Index: 1590254 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0951. Min Range: -0.0951
Max Act: 0.0808. Min Act: -0.0002
Data Index: 1625586 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0951. Min Range: -0.0951
Max Act: 0.0751. Min Act: -0.0002
Data Index: 495462 (The Pile)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0951. Min Range: -0.0951
Max Act: 0.0795. Min Act: -0.0002
Data Index: 1645679 (The Pile)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0951. Min Range: -0.0951
Max Act: 0.0756. Min Act: -0.0002
Data Index: 1166962 (The Pile)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0951. Min Range: -0.0951
Max Act: 0.0787. Min Act: -0.0002
Data Index: 1173823 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0951. Min Range: -0.0951
Max Act: 0.0702. Min Act: -0.0002
Data Index: 1933786 (The Pile)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0951. Min Range: -0.0951
Max Act: 0.0756. Min Act: -0.0002
Data Index: 805109 (The Pile)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0951. Min Range: -0.0951
Max Act: 0.0684. Min Act: -0.0002
Data Index: 1797518 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0951. Min Range: -0.0951
Max Act: 0.0770. Min Act: -0.0002
Data Index: 1367959 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0951. Min Range: -0.0951
Max Act: 0.0715. Min Act: -0.0002
Data Index: 433726 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0951. Min Range: -0.0951
Max Act: 0.0746. Min Act: -0.0002
Data Index: 1769568 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19