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

Dataset: The Pile

Neuron 4577 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: 0.0895. Min Range: -0.0895

Max Act: 0.0857. Min Act: -0.0000

Data Index: 428039 (The Pile)

Max Activating Token Index: 513

Text #1

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0669. Min Act: -0.0000

Data Index: 1174870 (The Pile)

Max Activating Token Index: 742

Text #2

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0895. Min Act: -0.0000

Data Index: 1847620 (The Pile)

Max Activating Token Index: 300

Text #3

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0743. Min Act: -0.0000

Data Index: 1177773 (The Pile)

Max Activating Token Index: 1000

Text #4

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0742. Min Act: -0.0000

Data Index: 406063 (The Pile)

Max Activating Token Index: 331

Text #5

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0678. Min Act: -0.0000

Data Index: 310992 (The Pile)

Max Activating Token Index: 667

Text #6

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0724. Min Act: -0.0000

Data Index: 774293 (The Pile)

Max Activating Token Index: 234

Text #7

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0639. Min Act: -0.0000

Data Index: 120213 (The Pile)

Max Activating Token Index: 1017

Text #8

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0742. Min Act: -0.0000

Data Index: 1979896 (The Pile)

Max Activating Token Index: 730

Text #9

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0695. Min Act: -0.0000

Data Index: 1995369 (The Pile)

Max Activating Token Index: 830

Text #10

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0798. Min Act: -0.0000

Data Index: 697334 (The Pile)

Max Activating Token Index: 244

Text #11

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0688. Min Act: -0.0000

Data Index: 1675125 (The Pile)

Max Activating Token Index: 152

Text #12

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0729. Min Act: -0.0000

Data Index: 1357182 (The Pile)

Max Activating Token Index: 471

Text #13

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0669. Min Act: -0.0000

Data Index: 25918 (The Pile)

Max Activating Token Index: 904

Text #14

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0676. Min Act: -0.0000

Data Index: 367225 (The Pile)

Max Activating Token Index: 336

Text #15

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0691. Min Act: -0.0000

Data Index: 1910441 (The Pile)

Max Activating Token Index: 891

Text #16

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0640. Min Act: -0.0000

Data Index: 828220 (The Pile)

Max Activating Token Index: 741

Text #17

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0668. Min Act: -0.0000

Data Index: 87711 (The Pile)

Max Activating Token Index: 751

Text #18

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0723. Min Act: -0.0000

Data Index: 1897743 (The Pile)

Max Activating Token Index: 139

Text #19

Max Range: 0.0895. Min Range: -0.0895

Max Act: 0.0644. Min Act: -0.0000

Data Index: 763696 (The Pile)

Max Activating Token Index: 694