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

Dataset: The Pile

Neuron 1639 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: 1.1220. Min Range: -1.1220

Max Act: 1.1220. Min Act: -0.0000

Data Index: 1321057 (The Pile)

Max Activating Token Index: 656

Text #1

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9456. Min Act: -0.0000

Data Index: 192263 (The Pile)

Max Activating Token Index: 147

Text #2

Max Range: 1.1220. Min Range: -1.1220

Max Act: 1.0754. Min Act: -0.0000

Data Index: 529166 (The Pile)

Max Activating Token Index: 977

Text #3

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9912. Min Act: -0.0000

Data Index: 1567271 (The Pile)

Max Activating Token Index: 949

Text #4

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9329. Min Act: -0.0000

Data Index: 855764 (The Pile)

Max Activating Token Index: 374

Text #5

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9190. Min Act: -0.0000

Data Index: 790260 (The Pile)

Max Activating Token Index: 646

Text #6

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8314. Min Act: -0.0000

Data Index: 1976807 (The Pile)

Max Activating Token Index: 502

Text #7

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8816. Min Act: -0.0000

Data Index: 684721 (The Pile)

Max Activating Token Index: 213

Text #8

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9278. Min Act: -0.0000

Data Index: 1433430 (The Pile)

Max Activating Token Index: 910

Text #9

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.9069. Min Act: -0.0000

Data Index: 802284 (The Pile)

Max Activating Token Index: 48

Text #10

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8422. Min Act: -0.0000

Data Index: 221460 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1545496 (The Pile)

Max Activating Token Index: 829

Text #12

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8376. Min Act: -0.0000

Data Index: 463645 (The Pile)

Max Activating Token Index: 838

Text #13

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8813. Min Act: -0.0000

Data Index: 1773535 (The Pile)

Max Activating Token Index: 652

Text #14

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8202. Min Act: -0.0000

Data Index: 765503 (The Pile)

Max Activating Token Index: 657

Text #15

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8248. Min Act: -0.0000

Data Index: 703276 (The Pile)

Max Activating Token Index: 903

Text #16

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8223. Min Act: -0.0000

Data Index: 129874 (The Pile)

Max Activating Token Index: 615

Text #17

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7839. Min Act: -0.0000

Data Index: 1757496 (The Pile)

Max Activating Token Index: 842

Text #18

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.8125. Min Act: -0.0000

Data Index: 608854 (The Pile)

Max Activating Token Index: 60

Text #19

Max Range: 1.1220. Min Range: -1.1220

Max Act: 0.7995. Min Act: -0.0000

Data Index: 503248 (The Pile)

Max Activating Token Index: 981