Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2684 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.3320. Min Act: -0.0000

Data Index: 1296558 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2327. Min Act: -0.0000

Data Index: 731375 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2398. Min Act: -0.0000

Data Index: 379999 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2334. Min Act: -0.0000

Data Index: 34260 (C4 (Web Text))

Max Activating Token Index: 321

Text #4

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2303. Min Act: -0.0000

Data Index: 652575 (C4 (Web Text))

Max Activating Token Index: 588

Text #5

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2298. Min Act: -0.0000

Data Index: 284400 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2234. Min Act: -0.0000

Data Index: 1129730 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2269. Min Act: -0.0000

Data Index: 363210 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2316. Min Act: -0.0000

Data Index: 601148 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1322161 (C4 (Web Text))

Max Activating Token Index: 531

Text #10

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2330. Min Act: -0.0000

Data Index: 567073 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2243. Min Act: -0.0001

Data Index: 391442 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2289. Min Act: -0.0000

Data Index: 1046482 (C4 (Web Text))

Max Activating Token Index: 375

Text #13

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2240. Min Act: -0.0000

Data Index: 29310 (C4 (Web Text))

Max Activating Token Index: 664

Text #14

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2185. Min Act: -0.0000

Data Index: 866154 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2026. Min Act: -0.0001

Data Index: 607261 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2235. Min Act: -0.0000

Data Index: 310690 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2142. Min Act: -0.0000

Data Index: 208323 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2123. Min Act: -0.0000

Data Index: 750858 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 0.3320. Min Range: -0.3320

Max Act: 0.2192. Min Act: -0.0001

Data Index: 1036568 (C4 (Web Text))

Max Activating Token Index: 840