Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 554 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0900. Min Range: -0.0900
Max Act: 0.0900. Min Act: -0.0001
Data Index: 164322 (The Pile)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0900. Min Range: -0.0900
Max Act: 0.0844. Min Act: -0.0001
Data Index: 875021 (The Pile)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0900. Min Range: -0.0900
Max Act: 0.0815. Min Act: -0.0001
Data Index: 1026321 (The Pile)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0900. Min Range: -0.0900
Max Act: 0.0831. Min Act: -0.0001
Data Index: 545387 (The Pile)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0900. Min Range: -0.0900
Max Act: 0.0796. Min Act: -0.0001
Data Index: 629712 (The Pile)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0900. Min Range: -0.0900
Max Act: 0.0795. Min Act: -0.0001
Data Index: 1895945 (The Pile)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0900. Min Range: -0.0900
Max Act: 0.0802. Min Act: -0.0001
Data Index: 839116 (The Pile)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0900. Min Range: -0.0900
Max Act: 0.0785. Min Act: -0.0001
Data Index: 1863909 (The Pile)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0900. Min Range: -0.0900
Max Act: 0.0704. Min Act: -0.0001
Data Index: 314455 (The Pile)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0900. Min Range: -0.0900
Max Act: 0.0850. Min Act: -0.0001
Data Index: 147513 (The Pile)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0900. Min Range: -0.0900
Max Act: 0.0667. Min Act: -0.0001
Data Index: 1788466 (The Pile)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0900. Min Range: -0.0900
Max Act: 0.0698. Min Act: -0.0001
Data Index: 837442 (The Pile)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0900. Min Range: -0.0900
Max Act: 0.0750. Min Act: -0.0001
Data Index: 1902241 (The Pile)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0900. Min Range: -0.0900
Max Act: 0.0713. Min Act: -0.0001
Data Index: 659729 (The Pile)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0900. Min Range: -0.0900
Max Act: 0.0710. Min Act: -0.0001
Data Index: 274944 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0900. Min Range: -0.0900
Max Act: 0.0702. Min Act: -0.0001
Data Index: 773939 (The Pile)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0900. Min Range: -0.0900
Max Act: 0.0710. Min Act: -0.0001
Data Index: 936346 (The Pile)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0900. Min Range: -0.0900
Max Act: 0.0667. Min Act: -0.0001
Data Index: 1768272 (The Pile)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0900. Min Range: -0.0900
Max Act: 0.0668. Min Act: -0.0001
Data Index: 1285208 (The Pile)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0900. Min Range: -0.0900
Max Act: 0.0692. Min Act: -0.0001
Data Index: 451418 (The Pile)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19