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

Dataset: The Pile

Neuron 1222 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: 0.6411. Min Range: -0.6411

Max Act: 0.6411. Min Act: -0.0000

Data Index: 423273 (The Pile)

Max Activating Token Index: 151

Text #1

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.6390. Min Act: -0.0000

Data Index: 1436160 (The Pile)

Max Activating Token Index: 491

Text #2

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.6246. Min Act: -0.0000

Data Index: 753193 (The Pile)

Max Activating Token Index: 101

Text #3

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5634. Min Act: -0.0000

Data Index: 325432 (The Pile)

Max Activating Token Index: 953

Text #4

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5301. Min Act: -0.0000

Data Index: 935764 (The Pile)

Max Activating Token Index: 945

Text #5

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5310. Min Act: -0.0000

Data Index: 312851 (The Pile)

Max Activating Token Index: 976

Text #6

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5669. Min Act: -0.0000

Data Index: 617493 (The Pile)

Max Activating Token Index: 83

Text #7

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5624. Min Act: -0.0000

Data Index: 847982 (The Pile)

Max Activating Token Index: 130

Text #8

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5414. Min Act: -0.0000

Data Index: 1127801 (The Pile)

Max Activating Token Index: 745

Text #9

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5214. Min Act: -0.0000

Data Index: 127523 (The Pile)

Max Activating Token Index: 145

Text #10

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4765. Min Act: -0.0000

Data Index: 922970 (The Pile)

Max Activating Token Index: 336

Text #11

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5009. Min Act: -0.0000

Data Index: 234339 (The Pile)

Max Activating Token Index: 110

Text #12

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.5293. Min Act: -0.0000

Data Index: 1685062 (The Pile)

Max Activating Token Index: 698

Text #13

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4702. Min Act: -0.0000

Data Index: 1834104 (The Pile)

Max Activating Token Index: 594

Text #14

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4236. Min Act: -0.0000

Data Index: 1657682 (The Pile)

Max Activating Token Index: 961

Text #15

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4861. Min Act: -0.0000

Data Index: 178223 (The Pile)

Max Activating Token Index: 59

Text #16

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4574. Min Act: -0.0000

Data Index: 1275522 (The Pile)

Max Activating Token Index: 691

Text #17

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4747. Min Act: -0.0000

Data Index: 1703937 (The Pile)

Max Activating Token Index: 431

Text #18

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4326. Min Act: -0.0000

Data Index: 899575 (The Pile)

Max Activating Token Index: 284

Text #19

Max Range: 0.6411. Min Range: -0.6411

Max Act: 0.4688. Min Act: -0.0000

Data Index: 152976 (The Pile)

Max Activating Token Index: 425