Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2432 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.7247. Min Act: -0.0000

Data Index: 581386 (The Pile)

Max Activating Token Index: 68

Text #1

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.7002. Min Act: -0.0000

Data Index: 382323 (The Pile)

Max Activating Token Index: 736

Text #2

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.6619. Min Act: -0.0000

Data Index: 515464 (The Pile)

Max Activating Token Index: 581

Text #3

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.6346. Min Act: -0.0000

Data Index: 89915 (The Pile)

Max Activating Token Index: 805

Text #4

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.6723. Min Act: -0.0000

Data Index: 1360459 (The Pile)

Max Activating Token Index: 33

Text #5

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5793. Min Act: -0.0000

Data Index: 1955787 (The Pile)

Max Activating Token Index: 203

Text #6

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1055195 (The Pile)

Max Activating Token Index: 580

Text #7

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.6426. Min Act: -0.0000

Data Index: 813313 (The Pile)

Max Activating Token Index: 676

Text #8

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5904. Min Act: -0.0000

Data Index: 1111479 (The Pile)

Max Activating Token Index: 279

Text #9

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5712. Min Act: -0.0000

Data Index: 1833187 (The Pile)

Max Activating Token Index: 354

Text #10

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1007799 (The Pile)

Max Activating Token Index: 456

Text #11

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5586. Min Act: -0.0000

Data Index: 216926 (The Pile)

Max Activating Token Index: 183

Text #12

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5755. Min Act: -0.0000

Data Index: 712759 (The Pile)

Max Activating Token Index: 863

Text #13

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5521. Min Act: -0.0000

Data Index: 902349 (The Pile)

Max Activating Token Index: 978

Text #14

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5447. Min Act: -0.0000

Data Index: 372141 (The Pile)

Max Activating Token Index: 889

Text #15

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5612. Min Act: -0.0000

Data Index: 968982 (The Pile)

Max Activating Token Index: 165

Text #16

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5554. Min Act: -0.0000

Data Index: 435967 (The Pile)

Max Activating Token Index: 801

Text #17

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5562. Min Act: -0.0000

Data Index: 910376 (The Pile)

Max Activating Token Index: 800

Text #18

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5336. Min Act: -0.0000

Data Index: 555879 (The Pile)

Max Activating Token Index: 329

Text #19

Max Range: 0.7247. Min Range: -0.7247

Max Act: 0.5534. Min Act: -0.0000

Data Index: 668557 (The Pile)

Max Activating Token Index: 280