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

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

Neuron 2089 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1440. Min Act: -0.0001

Data Index: 553949 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1421. Min Act: -0.0001

Data Index: 455991 (C4 (Web Text))

Max Activating Token Index: 166

Text #2

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1381. Min Act: -0.0001

Data Index: 1016467 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1348. Min Act: -0.0001

Data Index: 597029 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1303. Min Act: -0.0001

Data Index: 1066495 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1254. Min Act: -0.0001

Data Index: 800932 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1289. Min Act: -0.0001

Data Index: 1290777 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1280. Min Act: -0.0001

Data Index: 160158 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1315. Min Act: -0.0001

Data Index: 212467 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1279. Min Act: -0.0001

Data Index: 459060 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1199. Min Act: -0.0001

Data Index: 788628 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1196. Min Act: -0.0001

Data Index: 1243002 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1159. Min Act: -0.0001

Data Index: 967736 (C4 (Web Text))

Max Activating Token Index: 400

Text #13

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1225. Min Act: -0.0001

Data Index: 775951 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1184. Min Act: -0.0001

Data Index: 350019 (C4 (Web Text))

Max Activating Token Index: 110

Text #15

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1193. Min Act: -0.0001

Data Index: 347809 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1258. Min Act: -0.0001

Data Index: 393319 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1197. Min Act: -0.0001

Data Index: 343198 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1206. Min Act: -0.0001

Data Index: 1044684 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1191. Min Act: -0.0001

Data Index: 350261 (C4 (Web Text))

Max Activating Token Index: 686