Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 288 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1460. Min Act: -0.0002

Data Index: 517952 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1336. Min Act: -0.0002

Data Index: 834755 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1368. Min Act: -0.0002

Data Index: 764923 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1258. Min Act: -0.0002

Data Index: 1231673 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1304. Min Act: -0.0002

Data Index: 1080136 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1343. Min Act: -0.0002

Data Index: 216808 (C4 (Web Text))

Max Activating Token Index: 455

Text #6

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1233. Min Act: 0.0000

Data Index: 472781 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1222. Min Act: -0.0002

Data Index: 635141 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1256. Min Act: -0.0001

Data Index: 74846 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1265. Min Act: 0.0000

Data Index: 885731 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1233. Min Act: -0.0002

Data Index: 882031 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1255. Min Act: -0.0002

Data Index: 1097480 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1218. Min Act: -0.0002

Data Index: 820261 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1216. Min Act: -0.0002

Data Index: 183304 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1166. Min Act: -0.0002

Data Index: 1098605 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1200. Min Act: -0.0002

Data Index: 320444 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1188. Min Act: -0.0002

Data Index: 611114 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1178. Min Act: -0.0002

Data Index: 1194348 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1192. Min Act: -0.0002

Data Index: 208333 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 0.1460. Min Range: -0.1460

Max Act: 0.1149. Min Act: -0.0002

Data Index: 1213891 (C4 (Web Text))

Max Activating Token Index: 847