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

Dataset: The Pile

Neuron 537 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: 1.5332. Min Range: -1.5332

Max Act: 1.4558. Min Act: -0.0000

Data Index: 1923631 (The Pile)

Max Activating Token Index: 257

Text #1

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.4187. Min Act: -0.0000

Data Index: 1963444 (The Pile)

Max Activating Token Index: 810

Text #2

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.5332. Min Act: -0.0000

Data Index: 584778 (The Pile)

Max Activating Token Index: 63

Text #3

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.4349. Min Act: -0.0000

Data Index: 183428 (The Pile)

Max Activating Token Index: 556

Text #4

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.4429. Min Act: -0.0000

Data Index: 1707156 (The Pile)

Max Activating Token Index: 575

Text #5

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.4268. Min Act: -0.0000

Data Index: 1348525 (The Pile)

Max Activating Token Index: 78

Text #6

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.3429. Min Act: -0.0000

Data Index: 1709630 (The Pile)

Max Activating Token Index: 368

Text #7

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.3447. Min Act: -0.0000

Data Index: 1653189 (The Pile)

Max Activating Token Index: 551

Text #8

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.3278. Min Act: -0.0000

Data Index: 976768 (The Pile)

Max Activating Token Index: 610

Text #9

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.3078. Min Act: -0.0000

Data Index: 1837907 (The Pile)

Max Activating Token Index: 466

Text #10

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.2849. Min Act: -0.0000

Data Index: 1940622 (The Pile)

Max Activating Token Index: 999

Text #11

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.2267. Min Act: -0.0000

Data Index: 1961172 (The Pile)

Max Activating Token Index: 21

Text #12

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.2119. Min Act: -0.0000

Data Index: 1607995 (The Pile)

Max Activating Token Index: 752

Text #13

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.1400. Min Act: -0.0000

Data Index: 1283951 (The Pile)

Max Activating Token Index: 649

Text #14

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.1365. Min Act: -0.0000

Data Index: 671632 (The Pile)

Max Activating Token Index: 695

Text #15

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.1804. Min Act: -0.0000

Data Index: 1578279 (The Pile)

Max Activating Token Index: 401

Text #16

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.2354. Min Act: -0.0000

Data Index: 1846235 (The Pile)

Max Activating Token Index: 922

Text #17

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.2229. Min Act: -0.0000

Data Index: 1110432 (The Pile)

Max Activating Token Index: 1019

Text #18

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.1344. Min Act: -0.0000

Data Index: 306257 (The Pile)

Max Activating Token Index: 800

Text #19

Max Range: 1.5332. Min Range: -1.5332

Max Act: 1.1348. Min Act: -0.0000

Data Index: 715886 (The Pile)

Max Activating Token Index: 308