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

Dataset: The Pile

Neuron 3771 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.8178. Min Act: -0.0000

Data Index: 693873 (The Pile)

Max Activating Token Index: 527

Text #1

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7712. Min Act: -0.0000

Data Index: 67159 (The Pile)

Max Activating Token Index: 544

Text #2

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6687. Min Act: -0.0000

Data Index: 573427 (The Pile)

Max Activating Token Index: 176

Text #3

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.7622. Min Act: -0.0000

Data Index: 1557458 (The Pile)

Max Activating Token Index: 965

Text #4

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6821. Min Act: -0.0000

Data Index: 1143177 (The Pile)

Max Activating Token Index: 258

Text #5

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6665. Min Act: -0.0000

Data Index: 1754620 (The Pile)

Max Activating Token Index: 66

Text #6

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6870. Min Act: -0.0000

Data Index: 1737063 (The Pile)

Max Activating Token Index: 235

Text #7

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6652. Min Act: -0.0000

Data Index: 681079 (The Pile)

Max Activating Token Index: 401

Text #8

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6601. Min Act: -0.0000

Data Index: 243130 (The Pile)

Max Activating Token Index: 315

Text #9

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1381768 (The Pile)

Max Activating Token Index: 37

Text #10

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6511. Min Act: -0.0000

Data Index: 38408 (The Pile)

Max Activating Token Index: 790

Text #11

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1220784 (The Pile)

Max Activating Token Index: 331

Text #12

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6401. Min Act: -0.0000

Data Index: 1580710 (The Pile)

Max Activating Token Index: 605

Text #13

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1733833 (The Pile)

Max Activating Token Index: 452

Text #14

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.6081. Min Act: -0.0000

Data Index: 493244 (The Pile)

Max Activating Token Index: 33

Text #15

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.5989. Min Act: -0.0000

Data Index: 1901468 (The Pile)

Max Activating Token Index: 534

Text #16

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.5843. Min Act: -0.0000

Data Index: 119549 (The Pile)

Max Activating Token Index: 129

Text #17

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.5731. Min Act: -0.0000

Data Index: 1014776 (The Pile)

Max Activating Token Index: 107

Text #18

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.5399. Min Act: -0.0000

Data Index: 290422 (The Pile)

Max Activating Token Index: 250

Text #19

Max Range: 0.8178. Min Range: -0.8178

Max Act: 0.5537. Min Act: -0.0000

Data Index: 1707306 (The Pile)

Max Activating Token Index: 404