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

Dataset: The Pile

Neuron 1595 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.4659. Min Act: -0.0000

Data Index: 1416930 (The Pile)

Max Activating Token Index: 250

Text #1

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.3117. Min Act: -0.0000

Data Index: 253326 (The Pile)

Max Activating Token Index: 1017

Text #2

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.3627. Min Act: -0.0000

Data Index: 815270 (The Pile)

Max Activating Token Index: 5

Text #3

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.3002. Min Act: -0.0000

Data Index: 237730 (The Pile)

Max Activating Token Index: 716

Text #4

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.2294. Min Act: -0.0000

Data Index: 196669 (The Pile)

Max Activating Token Index: 428

Text #5

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.2490. Min Act: -0.0000

Data Index: 1384193 (The Pile)

Max Activating Token Index: 6

Text #6

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.2335. Min Act: -0.0000

Data Index: 1618034 (The Pile)

Max Activating Token Index: 389

Text #7

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.2779. Min Act: -0.0000

Data Index: 1496843 (The Pile)

Max Activating Token Index: 885

Text #8

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.1815. Min Act: -0.0000

Data Index: 934617 (The Pile)

Max Activating Token Index: 1020

Text #9

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0750. Min Act: -0.0000

Data Index: 906707 (The Pile)

Max Activating Token Index: 922

Text #10

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.1063. Min Act: -0.0000

Data Index: 900408 (The Pile)

Max Activating Token Index: 22

Text #11

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.1459. Min Act: -0.0000

Data Index: 1100843 (The Pile)

Max Activating Token Index: 11

Text #12

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0170. Min Act: -0.0000

Data Index: 1453889 (The Pile)

Max Activating Token Index: 767

Text #13

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0315. Min Act: -0.0000

Data Index: 1635038 (The Pile)

Max Activating Token Index: 46

Text #14

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.9959. Min Act: -0.0000

Data Index: 1688137 (The Pile)

Max Activating Token Index: 248

Text #15

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0239. Min Act: -0.0000

Data Index: 1814111 (The Pile)

Max Activating Token Index: 13

Text #16

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0270. Min Act: -0.0000

Data Index: 389592 (The Pile)

Max Activating Token Index: 651

Text #17

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.9432. Min Act: -0.0000

Data Index: 989552 (The Pile)

Max Activating Token Index: 878

Text #18

Max Range: 1.4659. Min Range: -1.4659

Max Act: 1.0383. Min Act: -0.0000

Data Index: 691453 (The Pile)

Max Activating Token Index: 616

Text #19

Max Range: 1.4659. Min Range: -1.4659

Max Act: 0.9667. Min Act: -0.0000

Data Index: 1608856 (The Pile)

Max Activating Token Index: 335