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

Dataset: The Pile

Neuron 117 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: 3.9756. Min Range: -3.9756

Max Act: 3.3707. Min Act: -0.0000

Data Index: 1141820 (The Pile)

Max Activating Token Index: 629

Text #1

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.9756. Min Act: -0.0000

Data Index: 1129568 (The Pile)

Max Activating Token Index: 121

Text #2

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.6038. Min Act: -0.0000

Data Index: 1006071 (The Pile)

Max Activating Token Index: 249

Text #3

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.4839. Min Act: -0.0000

Data Index: 1514078 (The Pile)

Max Activating Token Index: 968

Text #4

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.1463. Min Act: -0.0000

Data Index: 1716468 (The Pile)

Max Activating Token Index: 575

Text #5

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.1298. Min Act: -0.0000

Data Index: 1183461 (The Pile)

Max Activating Token Index: 267

Text #6

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.1419. Min Act: -0.0000

Data Index: 190221 (The Pile)

Max Activating Token Index: 942

Text #7

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.1245. Min Act: -0.0000

Data Index: 1475407 (The Pile)

Max Activating Token Index: 253

Text #8

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.2324. Min Act: -0.0000

Data Index: 299693 (The Pile)

Max Activating Token Index: 50

Text #9

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.2291. Min Act: -0.0000

Data Index: 1098984 (The Pile)

Max Activating Token Index: 542

Text #10

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.1774. Min Act: -0.0000

Data Index: 1174389 (The Pile)

Max Activating Token Index: 776

Text #11

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.0332. Min Act: -0.0000

Data Index: 435543 (The Pile)

Max Activating Token Index: 319

Text #12

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.1738. Min Act: -0.0000

Data Index: 1605568 (The Pile)

Max Activating Token Index: 258

Text #13

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.1271. Min Act: -0.0000

Data Index: 979349 (The Pile)

Max Activating Token Index: 14

Text #14

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.2678. Min Act: -0.0000

Data Index: 1877999 (The Pile)

Max Activating Token Index: 631

Text #15

Max Range: 3.9756. Min Range: -3.9756

Max Act: 2.9603. Min Act: -0.0000

Data Index: 1631927 (The Pile)

Max Activating Token Index: 588

Text #16

Max Range: 3.9756. Min Range: -3.9756

Max Act: 2.9531. Min Act: -0.0000

Data Index: 429023 (The Pile)

Max Activating Token Index: 328

Text #17

Max Range: 3.9756. Min Range: -3.9756

Max Act: 2.9651. Min Act: -0.0000

Data Index: 1388374 (The Pile)

Max Activating Token Index: 9

Text #18

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.1055. Min Act: -0.0000

Data Index: 1313307 (The Pile)

Max Activating Token Index: 607

Text #19

Max Range: 3.9756. Min Range: -3.9756

Max Act: 3.2200. Min Act: -0.0000

Data Index: 43718 (The Pile)

Max Activating Token Index: 522