Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1523 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0290. Min Act: -0.0004

Data Index: 573613 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0244. Min Act: -0.0004

Data Index: 1560015 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0264. Min Act: -0.0004

Data Index: 303203 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0247. Min Act: -0.0004

Data Index: 1342506 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0227. Min Act: -0.0004

Data Index: 921919 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0225. Min Act: -0.0004

Data Index: 1456859 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0239. Min Act: -0.0004

Data Index: 548906 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0243. Min Act: -0.0004

Data Index: 1520924 (Python Code)

Max Activating Token Index: 584

Text #8

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0259. Min Act: -0.0004

Data Index: 184722 (C4 (Web Text))

Max Activating Token Index: 846

Text #9

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0234. Min Act: -0.0004

Data Index: 802872 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0244. Min Act: -0.0004

Data Index: 1246949 (C4 (Web Text))

Max Activating Token Index: 676

Text #11

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0224. Min Act: -0.0004

Data Index: 517671 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0195. Min Act: -0.0004

Data Index: 628764 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0234. Min Act: -0.0004

Data Index: 124207 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0223. Min Act: -0.0004

Data Index: 1069613 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0210. Min Act: -0.0004

Data Index: 263657 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0203. Min Act: -0.0004

Data Index: 510748 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0206. Min Act: -0.0004

Data Index: 308483 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0209. Min Act: -0.0004

Data Index: 693626 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0212. Min Act: -0.0004

Data Index: 1065008 (C4 (Web Text))

Max Activating Token Index: 318