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

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

Neuron 3203 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1494. Min Act: -0.0002

Data Index: 801399 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1229. Min Act: -0.0002

Data Index: 16708 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1235. Min Act: -0.0002

Data Index: 742848 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1307. Min Act: -0.0002

Data Index: 1132312 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1217. Min Act: -0.0002

Data Index: 83328 (C4 (Web Text))

Max Activating Token Index: 251

Text #5

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1269. Min Act: -0.0002

Data Index: 265605 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1314. Min Act: -0.0002

Data Index: 1256469 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1177. Min Act: -0.0002

Data Index: 802360 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1244. Min Act: -0.0002

Data Index: 895500 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.0914. Min Act: -0.0002

Data Index: 735694 (C4 (Web Text))

Max Activating Token Index: 162

Text #10

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1327. Min Act: -0.0002

Data Index: 1034177 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1187. Min Act: -0.0002

Data Index: 1185009 (C4 (Web Text))

Max Activating Token Index: 623

Text #12

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1283. Min Act: -0.0002

Data Index: 630095 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1126. Min Act: -0.0002

Data Index: 1299163 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1152. Min Act: -0.0002

Data Index: 1211131 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1203. Min Act: -0.0002

Data Index: 1239984 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1112. Min Act: -0.0002

Data Index: 330594 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1212. Min Act: -0.0002

Data Index: 1030403 (C4 (Web Text))

Max Activating Token Index: 750

Text #18

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1044. Min Act: -0.0002

Data Index: 875427 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1163. Min Act: -0.0002

Data Index: 435924 (C4 (Web Text))

Max Activating Token Index: 208