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

Dataset: The Pile

Neuron 3417 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: 1.5033. Min Range: -1.5033

Max Act: 1.5033. Min Act: -0.0000

Data Index: 108328 (The Pile)

Max Activating Token Index: 588

Text #1

Max Range: 1.5033. Min Range: -1.5033

Max Act: 1.4655. Min Act: -0.0000

Data Index: 1303922 (The Pile)

Max Activating Token Index: 782

Text #2

Max Range: 1.5033. Min Range: -1.5033

Max Act: 1.3918. Min Act: -0.0000

Data Index: 1161362 (The Pile)

Max Activating Token Index: 299

Text #3

Max Range: 1.5033. Min Range: -1.5033

Max Act: 1.4205. Min Act: -0.0000

Data Index: 851042 (The Pile)

Max Activating Token Index: 196

Text #4

Max Range: 1.5033. Min Range: -1.5033

Max Act: 1.3564. Min Act: -0.0000

Data Index: 92696 (The Pile)

Max Activating Token Index: 406

Text #5

Max Range: 1.5033. Min Range: -1.5033

Max Act: 1.2614. Min Act: -0.0000

Data Index: 60926 (The Pile)

Max Activating Token Index: 655

Text #6

Max Range: 1.5033. Min Range: -1.5033

Max Act: 1.2534. Min Act: -0.0000

Data Index: 852552 (The Pile)

Max Activating Token Index: 626

Text #7

Max Range: 1.5033. Min Range: -1.5033

Max Act: 1.3087. Min Act: -0.0000

Data Index: 886060 (The Pile)

Max Activating Token Index: 859

Text #8

Max Range: 1.5033. Min Range: -1.5033

Max Act: 1.2243. Min Act: -0.0000

Data Index: 590871 (The Pile)

Max Activating Token Index: 458

Text #9

Max Range: 1.5033. Min Range: -1.5033

Max Act: 1.1423. Min Act: -0.0000

Data Index: 396702 (The Pile)

Max Activating Token Index: 154

Text #10

Max Range: 1.5033. Min Range: -1.5033

Max Act: 1.2091. Min Act: -0.0000

Data Index: 202571 (The Pile)

Max Activating Token Index: 698

Text #11

Max Range: 1.5033. Min Range: -1.5033

Max Act: 1.2034. Min Act: -0.0000

Data Index: 1303984 (The Pile)

Max Activating Token Index: 416

Text #12

Max Range: 1.5033. Min Range: -1.5033

Max Act: 1.1907. Min Act: -0.0000

Data Index: 225669 (The Pile)

Max Activating Token Index: 804

Text #13

Max Range: 1.5033. Min Range: -1.5033

Max Act: 1.1186. Min Act: -0.0000

Data Index: 443870 (The Pile)

Max Activating Token Index: 501

Text #14

Max Range: 1.5033. Min Range: -1.5033

Max Act: 1.1762. Min Act: -0.0000

Data Index: 295928 (The Pile)

Max Activating Token Index: 938

Text #15

Max Range: 1.5033. Min Range: -1.5033

Max Act: 1.1253. Min Act: -0.0000

Data Index: 1695008 (The Pile)

Max Activating Token Index: 297

Text #16

Max Range: 1.5033. Min Range: -1.5033

Max Act: 1.1131. Min Act: -0.0000

Data Index: 1303025 (The Pile)

Max Activating Token Index: 359

Text #17

Max Range: 1.5033. Min Range: -1.5033

Max Act: 1.0938. Min Act: -0.0000

Data Index: 663982 (The Pile)

Max Activating Token Index: 400

Text #18

Max Range: 1.5033. Min Range: -1.5033

Max Act: 1.1486. Min Act: -0.0000

Data Index: 359989 (The Pile)

Max Activating Token Index: 241

Text #19

Max Range: 1.5033. Min Range: -1.5033

Max Act: 1.0727. Min Act: -0.0000

Data Index: 691181 (The Pile)

Max Activating Token Index: 474