Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1885 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 5.1673. Min Range: -5.1673
Max Act: 5.0891. Min Act: 0.0000
Data Index: 1811137 (The Pile)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.6722. Min Act: 0.0002
Data Index: 1034714 (The Pile)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1673. Min Range: -5.1673
Max Act: 5.1673. Min Act: -0.0000
Data Index: 1376508 (The Pile)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.5648. Min Act: 0.0002
Data Index: 601667 (The Pile)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.1415. Min Act: 0.0001
Data Index: 1996005 (The Pile)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.4512. Min Act: -0.0000
Data Index: 564951 (The Pile)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.0448. Min Act: -0.0000
Data Index: 455078 (The Pile)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1673. Min Range: -5.1673
Max Act: 3.8715. Min Act: 0.0002
Data Index: 486703 (The Pile)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.0017. Min Act: 0.0000
Data Index: 1391820 (The Pile)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.3097. Min Act: -0.0000
Data Index: 961252 (The Pile)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.2848. Min Act: 0.0002
Data Index: 953630 (The Pile)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1673. Min Range: -5.1673
Max Act: 3.8614. Min Act: 0.0000
Data Index: 1656662 (The Pile)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1673. Min Range: -5.1673
Max Act: 3.9312. Min Act: 0.0000
Data Index: 387447 (The Pile)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1673. Min Range: -5.1673
Max Act: 3.7507. Min Act: 0.0000
Data Index: 82009 (The Pile)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1673. Min Range: -5.1673
Max Act: 3.9285. Min Act: 0.0002
Data Index: 288490 (The Pile)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1673. Min Range: -5.1673
Max Act: 3.7058. Min Act: -0.0000
Data Index: 497416 (The Pile)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1673. Min Range: -5.1673
Max Act: 3.9102. Min Act: 0.0001
Data Index: 1257823 (The Pile)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1673. Min Range: -5.1673
Max Act: 4.1566. Min Act: 0.0001
Data Index: 1086464 (The Pile)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1673. Min Range: -5.1673
Max Act: 3.6102. Min Act: -0.0000
Data Index: 614787 (The Pile)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1673. Min Range: -5.1673
Max Act: 3.6134. Min Act: -0.0000
Data Index: 1622088 (The Pile)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19