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

Dataset: The Pile

Neuron 801 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0621. Min Act: -0.0000

Data Index: 1715799 (The Pile)

Max Activating Token Index: 1017

Text #1

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0335. Min Act: -0.0000

Data Index: 571431 (The Pile)

Max Activating Token Index: 131

Text #2

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0314. Min Act: -0.0000

Data Index: 1671304 (The Pile)

Max Activating Token Index: 918

Text #3

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0268. Min Act: -0.0000

Data Index: 792311 (The Pile)

Max Activating Token Index: 74

Text #4

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0301. Min Act: -0.0000

Data Index: 1588876 (The Pile)

Max Activating Token Index: 904

Text #5

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0307. Min Act: -0.0000

Data Index: 360621 (The Pile)

Max Activating Token Index: 986

Text #6

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0300. Min Act: -0.0001

Data Index: 442479 (The Pile)

Max Activating Token Index: 734

Text #7

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0278. Min Act: -0.0000

Data Index: 1527873 (The Pile)

Max Activating Token Index: 696

Text #8

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0304. Min Act: -0.0000

Data Index: 1936425 (The Pile)

Max Activating Token Index: 751

Text #9

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0295. Min Act: -0.0000

Data Index: 1893856 (The Pile)

Max Activating Token Index: 206

Text #10

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0283. Min Act: -0.0000

Data Index: 282039 (The Pile)

Max Activating Token Index: 470

Text #11

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0282. Min Act: -0.0000

Data Index: 1643281 (The Pile)

Max Activating Token Index: 410

Text #12

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0254. Min Act: -0.0000

Data Index: 752008 (The Pile)

Max Activating Token Index: 653

Text #13

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0275. Min Act: -0.0000

Data Index: 1895514 (The Pile)

Max Activating Token Index: 338

Text #14

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0275. Min Act: -0.0000

Data Index: 1195400 (The Pile)

Max Activating Token Index: 233

Text #15

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0263. Min Act: -0.0000

Data Index: 792716 (The Pile)

Max Activating Token Index: 132

Text #16

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0270. Min Act: -0.0000

Data Index: 1169184 (The Pile)

Max Activating Token Index: 399

Text #17

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0268. Min Act: -0.0000

Data Index: 431073 (The Pile)

Max Activating Token Index: 644

Text #18

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0255. Min Act: -0.0000

Data Index: 886370 (The Pile)

Max Activating Token Index: 498

Text #19

Max Range: 0.0621. Min Range: -0.0621

Max Act: 0.0266. Min Act: -0.0000

Data Index: 1210467 (The Pile)

Max Activating Token Index: 331