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

Dataset: The Pile

Neuron 3629 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: 0.4667. Min Range: -0.4667

Max Act: 0.4614. Min Act: -0.0000

Data Index: 1367071 (The Pile)

Max Activating Token Index: 307

Text #1

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4667. Min Act: -0.0000

Data Index: 94055 (The Pile)

Max Activating Token Index: 697

Text #2

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4339. Min Act: -0.0000

Data Index: 1644168 (The Pile)

Max Activating Token Index: 401

Text #3

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4330. Min Act: -0.0000

Data Index: 384646 (The Pile)

Max Activating Token Index: 435

Text #4

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3521. Min Act: -0.0000

Data Index: 608427 (The Pile)

Max Activating Token Index: 896

Text #5

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1073072 (The Pile)

Max Activating Token Index: 812

Text #6

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3786. Min Act: -0.0000

Data Index: 330620 (The Pile)

Max Activating Token Index: 656

Text #7

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3916. Min Act: -0.0000

Data Index: 551326 (The Pile)

Max Activating Token Index: 86

Text #8

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3434. Min Act: -0.0000

Data Index: 1075163 (The Pile)

Max Activating Token Index: 39

Text #9

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3795. Min Act: -0.0000

Data Index: 1030834 (The Pile)

Max Activating Token Index: 7

Text #10

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3344. Min Act: -0.0000

Data Index: 1111127 (The Pile)

Max Activating Token Index: 544

Text #11

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3433. Min Act: -0.0000

Data Index: 1296572 (The Pile)

Max Activating Token Index: 988

Text #12

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3404. Min Act: -0.0000

Data Index: 1358228 (The Pile)

Max Activating Token Index: 939

Text #13

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3726. Min Act: -0.0000

Data Index: 957068 (The Pile)

Max Activating Token Index: 411

Text #14

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1162605 (The Pile)

Max Activating Token Index: 344

Text #15

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3288. Min Act: -0.0000

Data Index: 180146 (The Pile)

Max Activating Token Index: 612

Text #16

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3463. Min Act: -0.0000

Data Index: 1167450 (The Pile)

Max Activating Token Index: 224

Text #17

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1245161 (The Pile)

Max Activating Token Index: 59

Text #18

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3612. Min Act: -0.0000

Data Index: 1820293 (The Pile)

Max Activating Token Index: 177

Text #19

Max Range: 0.4667. Min Range: -0.4667

Max Act: 0.3567. Min Act: -0.0000

Data Index: 951646 (The Pile)

Max Activating Token Index: 93