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

Dataset: The Pile

Neuron 4637 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0490. Min Range: -1.0490

Max Act: 1.0490. Min Act: -0.0000

Data Index: 1652339 (The Pile)

Max Activating Token Index: 573

Text #1

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.9920. Min Act: -0.0000

Data Index: 518411 (The Pile)

Max Activating Token Index: 575

Text #2

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.9656. Min Act: -0.0000

Data Index: 1336904 (The Pile)

Max Activating Token Index: 328

Text #3

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.9301. Min Act: -0.0000

Data Index: 1556483 (The Pile)

Max Activating Token Index: 820

Text #4

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8940. Min Act: -0.0000

Data Index: 1158271 (The Pile)

Max Activating Token Index: 90

Text #5

Max Range: 1.0490. Min Range: -1.0490

Max Act: 1.0108. Min Act: -0.0000

Data Index: 121764 (The Pile)

Max Activating Token Index: 253

Text #6

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.7247. Min Act: -0.0000

Data Index: 382529 (The Pile)

Max Activating Token Index: 271

Text #7

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8558. Min Act: -0.0000

Data Index: 1543928 (The Pile)

Max Activating Token Index: 32

Text #8

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.7382. Min Act: -0.0000

Data Index: 565151 (The Pile)

Max Activating Token Index: 383

Text #9

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8198. Min Act: -0.0000

Data Index: 24261 (The Pile)

Max Activating Token Index: 339

Text #10

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8745. Min Act: -0.0000

Data Index: 1034274 (The Pile)

Max Activating Token Index: 1005

Text #11

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.9388. Min Act: -0.0000

Data Index: 746364 (The Pile)

Max Activating Token Index: 786

Text #12

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.7973. Min Act: -0.0000

Data Index: 570676 (The Pile)

Max Activating Token Index: 19

Text #13

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.8209. Min Act: -0.0000

Data Index: 562309 (The Pile)

Max Activating Token Index: 583

Text #14

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.6715. Min Act: -0.0000

Data Index: 1741865 (The Pile)

Max Activating Token Index: 878

Text #15

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1041762 (The Pile)

Max Activating Token Index: 569

Text #16

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.7347. Min Act: -0.0000

Data Index: 1923182 (The Pile)

Max Activating Token Index: 489

Text #17

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.7494. Min Act: -0.0000

Data Index: 1691213 (The Pile)

Max Activating Token Index: 496

Text #18

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.7691. Min Act: -0.0000

Data Index: 470112 (The Pile)

Max Activating Token Index: 412

Text #19

Max Range: 1.0490. Min Range: -1.0490

Max Act: 0.7378. Min Act: -0.0000

Data Index: 817826 (The Pile)

Max Activating Token Index: 10