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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4391 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7895. Min Range: -0.7895

Max Act: 0.7895. Min Act: -0.0000

Data Index: 117533 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 0.7895. Min Range: -0.7895

Max Act: 0.7473. Min Act: -0.0000

Data Index: 409936 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.7895. Min Range: -0.7895

Max Act: 0.7476. Min Act: -0.0000

Data Index: 1196703 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 0.7895. Min Range: -0.7895

Max Act: 0.7391. Min Act: -0.0000

Data Index: 855979 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 0.7895. Min Range: -0.7895

Max Act: 0.6479. Min Act: -0.0000

Data Index: 761512 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 0.7895. Min Range: -0.7895

Max Act: 0.6362. Min Act: -0.0000

Data Index: 898210 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.7895. Min Range: -0.7895

Max Act: 0.6494. Min Act: -0.0000

Data Index: 573239 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.7895. Min Range: -0.7895

Max Act: 0.5873. Min Act: -0.0000

Data Index: 245097 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 0.7895. Min Range: -0.7895

Max Act: 0.6698. Min Act: -0.0000

Data Index: 1083081 (C4 (Web Text))

Max Activating Token Index: 462

Text #9

Max Range: 0.7895. Min Range: -0.7895

Max Act: 0.6821. Min Act: -0.0000

Data Index: 720816 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 0.7895. Min Range: -0.7895

Max Act: 0.6344. Min Act: -0.0000

Data Index: 308225 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.7895. Min Range: -0.7895

Max Act: 0.6416. Min Act: -0.0000

Data Index: 215670 (C4 (Web Text))

Max Activating Token Index: 760

Text #12

Max Range: 0.7895. Min Range: -0.7895

Max Act: 0.6532. Min Act: -0.0000

Data Index: 205858 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 0.7895. Min Range: -0.7895

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1046807 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 0.7895. Min Range: -0.7895

Max Act: 0.6299. Min Act: -0.0000

Data Index: 929746 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 0.7895. Min Range: -0.7895

Max Act: 0.5741. Min Act: -0.0000

Data Index: 1044527 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 0.7895. Min Range: -0.7895

Max Act: 0.6243. Min Act: -0.0000

Data Index: 727634 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 0.7895. Min Range: -0.7895

Max Act: 0.6443. Min Act: -0.0000

Data Index: 1338311 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.7895. Min Range: -0.7895

Max Act: 0.5838. Min Act: 0.0000

Data Index: 704102 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 0.7895. Min Range: -0.7895

Max Act: 0.6255. Min Act: -0.0000

Data Index: 425730 (C4 (Web Text))

Max Activating Token Index: 108