Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1797 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1573. Min Act: -0.0002

Data Index: 20251 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1374. Min Act: -0.0002

Data Index: 525079 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1317. Min Act: -0.0002

Data Index: 262015 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1302. Min Act: -0.0002

Data Index: 9482 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1295. Min Act: -0.0002

Data Index: 6578 (C4 (Web Text))

Max Activating Token Index: 68

Text #5

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1279. Min Act: -0.0002

Data Index: 1258026 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1293. Min Act: -0.0002

Data Index: 1157430 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1276. Min Act: -0.0002

Data Index: 1042246 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1223. Min Act: -0.0002

Data Index: 619328 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1238. Min Act: -0.0002

Data Index: 1017808 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1225. Min Act: -0.0002

Data Index: 879760 (C4 (Web Text))

Max Activating Token Index: 349

Text #11

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1164. Min Act: -0.0002

Data Index: 165582 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1196. Min Act: -0.0002

Data Index: 873615 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1207. Min Act: -0.0002

Data Index: 1339083 (C4 (Web Text))

Max Activating Token Index: 555

Text #14

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1195. Min Act: -0.0002

Data Index: 700796 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1191. Min Act: -0.0002

Data Index: 1287466 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1179. Min Act: -0.0002

Data Index: 1179344 (C4 (Web Text))

Max Activating Token Index: 15

Text #17

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1182. Min Act: -0.0002

Data Index: 1111839 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1141. Min Act: -0.0002

Data Index: 880894 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.1573. Min Range: -0.1573

Max Act: 0.1177. Min Act: -0.0002

Data Index: 832909 (C4 (Web Text))

Max Activating Token Index: 8