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

Dataset: The Pile

Neuron 3168 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.4673. Min Act: -0.0000

Data Index: 338877 (The Pile)

Max Activating Token Index: 579

Text #1

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.4210. Min Act: -0.0000

Data Index: 475444 (The Pile)

Max Activating Token Index: 153

Text #2

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.4032. Min Act: -0.0000

Data Index: 1243446 (The Pile)

Max Activating Token Index: 136

Text #3

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.4145. Min Act: -0.0000

Data Index: 382523 (The Pile)

Max Activating Token Index: 179

Text #4

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1782482 (The Pile)

Max Activating Token Index: 929

Text #5

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.3730. Min Act: -0.0000

Data Index: 539668 (The Pile)

Max Activating Token Index: 822

Text #6

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.3871. Min Act: -0.0000

Data Index: 1203273 (The Pile)

Max Activating Token Index: 121

Text #7

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.3829. Min Act: -0.0000

Data Index: 874988 (The Pile)

Max Activating Token Index: 355

Text #8

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.3711. Min Act: -0.0000

Data Index: 1558815 (The Pile)

Max Activating Token Index: 679

Text #9

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.3821. Min Act: -0.0000

Data Index: 773923 (The Pile)

Max Activating Token Index: 418

Text #10

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.3901. Min Act: -0.0000

Data Index: 1405553 (The Pile)

Max Activating Token Index: 179

Text #11

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.3770. Min Act: -0.0001

Data Index: 93343 (The Pile)

Max Activating Token Index: 10

Text #12

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.3723. Min Act: -0.0000

Data Index: 1461601 (The Pile)

Max Activating Token Index: 516

Text #13

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.3453. Min Act: -0.0000

Data Index: 722962 (The Pile)

Max Activating Token Index: 220

Text #14

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.3693. Min Act: -0.0000

Data Index: 213063 (The Pile)

Max Activating Token Index: 297

Text #15

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.3539. Min Act: -0.0000

Data Index: 232333 (The Pile)

Max Activating Token Index: 847

Text #16

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.3905. Min Act: -0.0000

Data Index: 1164659 (The Pile)

Max Activating Token Index: 498

Text #17

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.3499. Min Act: -0.0000

Data Index: 360715 (The Pile)

Max Activating Token Index: 135

Text #18

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.3941. Min Act: -0.0000

Data Index: 1266478 (The Pile)

Max Activating Token Index: 568

Text #19

Max Range: 0.4673. Min Range: -0.4673

Max Act: 0.3581. Min Act: -0.0000

Data Index: 1090010 (The Pile)

Max Activating Token Index: 477