Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5518 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.3031. Min Act: -0.0000

Data Index: 421748 (C4 (Web Text))

Max Activating Token Index: 430

Text #1

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2419. Min Act: 0.0001

Data Index: 344251 (C4 (Web Text))

Max Activating Token Index: 342

Text #2

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2362. Min Act: -0.0000

Data Index: 936445 (C4 (Web Text))

Max Activating Token Index: 1017

Text #3

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2338. Min Act: 0.0001

Data Index: 190137 (C4 (Web Text))

Max Activating Token Index: 572

Text #4

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2131. Min Act: -0.0000

Data Index: 914898 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2333. Min Act: 0.0000

Data Index: 179865 (C4 (Web Text))

Max Activating Token Index: 861

Text #6

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2162. Min Act: -0.0000

Data Index: 342887 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2212. Min Act: -0.0000

Data Index: 726732 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2203. Min Act: -0.0000

Data Index: 344140 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2194. Min Act: -0.0000

Data Index: 219966 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2258. Min Act: 0.0000

Data Index: 855265 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2145. Min Act: 0.0000

Data Index: 1262392 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2213. Min Act: -0.0000

Data Index: 1296041 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2110. Min Act: 0.0000

Data Index: 1151717 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2196. Min Act: -0.0000

Data Index: 1032111 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1176206 (C4 (Web Text))

Max Activating Token Index: 67

Text #16

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2078. Min Act: 0.0000

Data Index: 930589 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2144. Min Act: -0.0000

Data Index: 57207 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2145. Min Act: 0.0000

Data Index: 903433 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.3031. Min Range: -0.3031

Max Act: 0.2078. Min Act: -0.0000

Data Index: 1229777 (C4 (Web Text))

Max Activating Token Index: 361