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

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

Neuron 4840 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0464. Min Act: -0.0002

Data Index: 460050 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0409. Min Act: -0.0002

Data Index: 930652 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0356. Min Act: -0.0002

Data Index: 592386 (C4 (Web Text))

Max Activating Token Index: 741

Text #3

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0342. Min Act: -0.0002

Data Index: 893432 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0314. Min Act: -0.0002

Data Index: 145382 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1222983 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0282. Min Act: -0.0002

Data Index: 388434 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0281. Min Act: -0.0002

Data Index: 921892 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0279. Min Act: -0.0002

Data Index: 912570 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0272. Min Act: -0.0002

Data Index: 1166702 (C4 (Web Text))

Max Activating Token Index: 666

Text #10

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0278. Min Act: -0.0002

Data Index: 535118 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0269. Min Act: -0.0002

Data Index: 518847 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0270. Min Act: -0.0002

Data Index: 332253 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0263. Min Act: -0.0002

Data Index: 348742 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0259. Min Act: -0.0002

Data Index: 252825 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0257. Min Act: -0.0002

Data Index: 147205 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0257. Min Act: -0.0002

Data Index: 1015280 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0255. Min Act: -0.0002

Data Index: 692583 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0253. Min Act: -0.0002

Data Index: 748129 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.0464. Min Range: -0.0464

Max Act: 0.0252. Min Act: -0.0002

Data Index: 382600 (C4 (Web Text))

Max Activating Token Index: 149