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

Dataset: The Pile

Neuron 3848 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0378. Min Act: 0.0000

Data Index: 950476 (The Pile)

Max Activating Token Index: 987

Text #1

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0355. Min Act: 0.0000

Data Index: 204210 (The Pile)

Max Activating Token Index: 705

Text #2

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0333. Min Act: -0.0000

Data Index: 175164 (The Pile)

Max Activating Token Index: 957

Text #3

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0324. Min Act: 0.0000

Data Index: 1614844 (The Pile)

Max Activating Token Index: 865

Text #4

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0315. Min Act: -0.0000

Data Index: 293519 (The Pile)

Max Activating Token Index: 736

Text #5

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0302. Min Act: 0.0000

Data Index: 313850 (The Pile)

Max Activating Token Index: 868

Text #6

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0303. Min Act: -0.0000

Data Index: 257531 (The Pile)

Max Activating Token Index: 811

Text #7

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0299. Min Act: -0.0000

Data Index: 1525635 (The Pile)

Max Activating Token Index: 878

Text #8

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0299. Min Act: -0.0000

Data Index: 347047 (The Pile)

Max Activating Token Index: 899

Text #9

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0295. Min Act: -0.0000

Data Index: 1524897 (The Pile)

Max Activating Token Index: 958

Text #10

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0294. Min Act: 0.0000

Data Index: 461501 (The Pile)

Max Activating Token Index: 906

Text #11

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0291. Min Act: -0.0000

Data Index: 133380 (The Pile)

Max Activating Token Index: 579

Text #12

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0300. Min Act: 0.0000

Data Index: 1193981 (The Pile)

Max Activating Token Index: 891

Text #13

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0282. Min Act: -0.0000

Data Index: 416411 (The Pile)

Max Activating Token Index: 990

Text #14

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0279. Min Act: -0.0000

Data Index: 861930 (The Pile)

Max Activating Token Index: 649

Text #15

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0277. Min Act: 0.0000

Data Index: 603390 (The Pile)

Max Activating Token Index: 979

Text #16

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0277. Min Act: -0.0000

Data Index: 1085727 (The Pile)

Max Activating Token Index: 974

Text #17

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0273. Min Act: -0.0000

Data Index: 33967 (The Pile)

Max Activating Token Index: 969

Text #18

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0264. Min Act: -0.0000

Data Index: 484251 (The Pile)

Max Activating Token Index: 1012

Text #19

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0273. Min Act: -0.0000

Data Index: 1323305 (The Pile)

Max Activating Token Index: 868