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

Dataset: The Pile

Neuron 4962 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: 1.5988. Min Range: -1.5988

Max Act: 1.5402. Min Act: -0.0000

Data Index: 893057 (The Pile)

Max Activating Token Index: 322

Text #1

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.5988. Min Act: -0.0000

Data Index: 1568853 (The Pile)

Max Activating Token Index: 844

Text #2

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.3898. Min Act: -0.0000

Data Index: 1443708 (The Pile)

Max Activating Token Index: 880

Text #3

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.2915. Min Act: -0.0000

Data Index: 1172829 (The Pile)

Max Activating Token Index: 907

Text #4

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.2917. Min Act: -0.0000

Data Index: 1812642 (The Pile)

Max Activating Token Index: 298

Text #5

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.4000. Min Act: -0.0000

Data Index: 1887639 (The Pile)

Max Activating Token Index: 412

Text #6

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.2494. Min Act: -0.0000

Data Index: 1094227 (The Pile)

Max Activating Token Index: 508

Text #7

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.3854. Min Act: -0.0000

Data Index: 1064226 (The Pile)

Max Activating Token Index: 1005

Text #8

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.2999. Min Act: -0.0000

Data Index: 1940005 (The Pile)

Max Activating Token Index: 375

Text #9

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.2928. Min Act: -0.0000

Data Index: 25471 (The Pile)

Max Activating Token Index: 759

Text #10

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.2867. Min Act: -0.0000

Data Index: 491852 (The Pile)

Max Activating Token Index: 578

Text #11

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.2667. Min Act: -0.0000

Data Index: 1109434 (The Pile)

Max Activating Token Index: 251

Text #12

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.3481. Min Act: -0.0000

Data Index: 1722927 (The Pile)

Max Activating Token Index: 159

Text #13

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.1934. Min Act: -0.0000

Data Index: 247147 (The Pile)

Max Activating Token Index: 955

Text #14

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.1968. Min Act: -0.0000

Data Index: 791962 (The Pile)

Max Activating Token Index: 248

Text #15

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.2174. Min Act: -0.0000

Data Index: 691386 (The Pile)

Max Activating Token Index: 565

Text #16

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.2382. Min Act: -0.0000

Data Index: 1264733 (The Pile)

Max Activating Token Index: 375

Text #17

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.2386. Min Act: -0.0000

Data Index: 767608 (The Pile)

Max Activating Token Index: 708

Text #18

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.2324. Min Act: -0.0000

Data Index: 65480 (The Pile)

Max Activating Token Index: 699

Text #19

Max Range: 1.5988. Min Range: -1.5988

Max Act: 1.1583. Min Act: -0.0000

Data Index: 1838798 (The Pile)

Max Activating Token Index: 429