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

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

Neuron 4289 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: 1.3023. Min Range: -1.3023

Max Act: 1.3023. Min Act: -0.0000

Data Index: 826551 (C4 (Web Text))

Max Activating Token Index: 427

Text #1

Max Range: 1.3023. Min Range: -1.3023

Max Act: 1.0590. Min Act: -0.0000

Data Index: 1322670 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 1.3023. Min Range: -1.3023

Max Act: 0.8795. Min Act: -0.0000

Data Index: 1373602 (Python Code)

Max Activating Token Index: 895

Text #3

Max Range: 1.3023. Min Range: -1.3023

Max Act: 0.9590. Min Act: -0.0000

Data Index: 446311 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 1.3023. Min Range: -1.3023

Max Act: 0.8913. Min Act: -0.0000

Data Index: 319112 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 1.3023. Min Range: -1.3023

Max Act: 0.8866. Min Act: 0.0000

Data Index: 734496 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 1.3023. Min Range: -1.3023

Max Act: 0.8282. Min Act: 0.0001

Data Index: 897778 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 1.3023. Min Range: -1.3023

Max Act: 0.8839. Min Act: -0.0000

Data Index: 1400546 (Python Code)

Max Activating Token Index: 872

Text #8

Max Range: 1.3023. Min Range: -1.3023

Max Act: 0.8322. Min Act: -0.0000

Data Index: 315929 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 1.3023. Min Range: -1.3023

Max Act: 0.8345. Min Act: -0.0000

Data Index: 508742 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 1.3023. Min Range: -1.3023

Max Act: 0.8273. Min Act: -0.0000

Data Index: 1633500 (Python Code)

Max Activating Token Index: 892

Text #11

Max Range: 1.3023. Min Range: -1.3023

Max Act: 0.8229. Min Act: 0.0000

Data Index: 1358334 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 1.3023. Min Range: -1.3023

Max Act: 0.8344. Min Act: -0.0000

Data Index: 1618719 (Python Code)

Max Activating Token Index: 1018

Text #13

Max Range: 1.3023. Min Range: -1.3023

Max Act: 0.8169. Min Act: -0.0000

Data Index: 1465346 (Python Code)

Max Activating Token Index: 920

Text #14

Max Range: 1.3023. Min Range: -1.3023

Max Act: 0.7988. Min Act: 0.0001

Data Index: 1324129 (C4 (Web Text))

Max Activating Token Index: 621

Text #15

Max Range: 1.3023. Min Range: -1.3023

Max Act: 0.7689. Min Act: -0.0000

Data Index: 677977 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 1.3023. Min Range: -1.3023

Max Act: 0.8196. Min Act: -0.0000

Data Index: 82378 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 1.3023. Min Range: -1.3023

Max Act: 0.7707. Min Act: 0.0001

Data Index: 813050 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 1.3023. Min Range: -1.3023

Max Act: 0.7359. Min Act: -0.0000

Data Index: 833200 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 1.3023. Min Range: -1.3023

Max Act: 0.7733. Min Act: -0.0000

Data Index: 1633698 (Python Code)

Max Activating Token Index: 543