Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 1412 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.1660. Min Act: -0.0000

Data Index: 1660951 (The Pile)

Max Activating Token Index: 785

Text #1

Max Range: 1.1660. Min Range: -1.1660

Max Act: 1.0592. Min Act: -0.0000

Data Index: 1076983 (The Pile)

Max Activating Token Index: 516

Text #2

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.7996. Min Act: -0.0000

Data Index: 221777 (The Pile)

Max Activating Token Index: 636

Text #3

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.8878. Min Act: -0.0000

Data Index: 1844403 (The Pile)

Max Activating Token Index: 369

Text #4

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.7281. Min Act: -0.0000

Data Index: 901408 (The Pile)

Max Activating Token Index: 664

Text #5

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.7119. Min Act: -0.0000

Data Index: 622914 (The Pile)

Max Activating Token Index: 640

Text #6

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.6603. Min Act: -0.0000

Data Index: 1423141 (The Pile)

Max Activating Token Index: 464

Text #7

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.6292. Min Act: -0.0000

Data Index: 1061811 (The Pile)

Max Activating Token Index: 669

Text #8

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.5998. Min Act: -0.0000

Data Index: 1388159 (The Pile)

Max Activating Token Index: 728

Text #9

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.6398. Min Act: -0.0000

Data Index: 886041 (The Pile)

Max Activating Token Index: 800

Text #10

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.5825. Min Act: -0.0000

Data Index: 62201 (The Pile)

Max Activating Token Index: 650

Text #11

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.5653. Min Act: -0.0000

Data Index: 694857 (The Pile)

Max Activating Token Index: 378

Text #12

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.5424. Min Act: -0.0000

Data Index: 279913 (The Pile)

Max Activating Token Index: 754

Text #13

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.5439. Min Act: -0.0000

Data Index: 580391 (The Pile)

Max Activating Token Index: 991

Text #14

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.5512. Min Act: -0.0000

Data Index: 1352915 (The Pile)

Max Activating Token Index: 894

Text #15

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.5302. Min Act: -0.0000

Data Index: 244870 (The Pile)

Max Activating Token Index: 152

Text #16

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.5255. Min Act: -0.0000

Data Index: 324738 (The Pile)

Max Activating Token Index: 719

Text #17

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.5098. Min Act: -0.0000

Data Index: 1382982 (The Pile)

Max Activating Token Index: 843

Text #18

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.5478. Min Act: 0.0000

Data Index: 939475 (The Pile)

Max Activating Token Index: 737

Text #19

Max Range: 1.1660. Min Range: -1.1660

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1712345 (The Pile)

Max Activating Token Index: 152