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

Dataset: The Pile

Neuron 3170 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2974. Min Act: -0.0000

Data Index: 518263 (The Pile)

Max Activating Token Index: 393

Text #1

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2809. Min Act: -0.0000

Data Index: 1368138 (The Pile)

Max Activating Token Index: 433

Text #2

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2826. Min Act: -0.0000

Data Index: 973953 (The Pile)

Max Activating Token Index: 444

Text #3

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2902. Min Act: -0.0000

Data Index: 8136 (The Pile)

Max Activating Token Index: 582

Text #4

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2613. Min Act: -0.0000

Data Index: 1110937 (The Pile)

Max Activating Token Index: 772

Text #5

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2541. Min Act: -0.0000

Data Index: 1761444 (The Pile)

Max Activating Token Index: 672

Text #6

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2568. Min Act: -0.0000

Data Index: 1336500 (The Pile)

Max Activating Token Index: 29

Text #7

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2765. Min Act: -0.0000

Data Index: 1587615 (The Pile)

Max Activating Token Index: 984

Text #8

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2886. Min Act: -0.0000

Data Index: 574774 (The Pile)

Max Activating Token Index: 864

Text #9

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1191342 (The Pile)

Max Activating Token Index: 496

Text #10

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2475. Min Act: -0.0000

Data Index: 78586 (The Pile)

Max Activating Token Index: 392

Text #11

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2468. Min Act: -0.0000

Data Index: 1867215 (The Pile)

Max Activating Token Index: 812

Text #12

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2389. Min Act: -0.0000

Data Index: 97452 (The Pile)

Max Activating Token Index: 887

Text #13

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2375. Min Act: -0.0000

Data Index: 1365577 (The Pile)

Max Activating Token Index: 357

Text #14

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2278. Min Act: -0.0000

Data Index: 1408580 (The Pile)

Max Activating Token Index: 363

Text #15

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2334. Min Act: -0.0000

Data Index: 1092471 (The Pile)

Max Activating Token Index: 716

Text #16

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2313. Min Act: -0.0000

Data Index: 1902416 (The Pile)

Max Activating Token Index: 760

Text #17

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2314. Min Act: -0.0000

Data Index: 1384061 (The Pile)

Max Activating Token Index: 323

Text #18

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2303. Min Act: -0.0000

Data Index: 1760697 (The Pile)

Max Activating Token Index: 373

Text #19

Max Range: 0.2974. Min Range: -0.2974

Max Act: 0.2228. Min Act: -0.0000

Data Index: 298059 (The Pile)

Max Activating Token Index: 35