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

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

Neuron 1988 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.8289. Min Act: -0.0002

Data Index: 344110 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.8511. Min Act: -0.0002

Data Index: 386909 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.7965. Min Act: -0.0002

Data Index: 1132916 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.7265. Min Act: -0.0002

Data Index: 861867 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.8040. Min Act: -0.0002

Data Index: 344826 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.7341. Min Act: -0.0002

Data Index: 837977 (C4 (Web Text))

Max Activating Token Index: 56

Text #6

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.6874. Min Act: -0.0002

Data Index: 612240 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.7176. Min Act: -0.0002

Data Index: 90742 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.7450. Min Act: -0.0002

Data Index: 259154 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.6222. Min Act: -0.0002

Data Index: 306287 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.7099. Min Act: -0.0002

Data Index: 191768 (C4 (Web Text))

Max Activating Token Index: 738

Text #11

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.8414. Min Act: -0.0002

Data Index: 442815 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.7210. Min Act: -0.0002

Data Index: 52248 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.7607. Min Act: -0.0002

Data Index: 786484 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.7228. Min Act: -0.0002

Data Index: 458107 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.6943. Min Act: -0.0002

Data Index: 9207 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.6437. Min Act: -0.0002

Data Index: 284244 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.7056. Min Act: -0.0002

Data Index: 552896 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.7749. Min Act: -0.0002

Data Index: 115947 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.8511. Min Range: -0.8511

Max Act: 0.7238. Min Act: -0.0002

Data Index: 277430 (C4 (Web Text))

Max Activating Token Index: 367