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

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

Neuron 1845 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1306. Min Act: -0.0001

Data Index: 842167 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1320593 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1248. Min Act: -0.0001

Data Index: 64447 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1315. Min Act: -0.0001

Data Index: 745956 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1201. Min Act: -0.0001

Data Index: 1314105 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1256. Min Act: -0.0001

Data Index: 267182 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1149. Min Act: -0.0001

Data Index: 1288887 (C4 (Web Text))

Max Activating Token Index: 338

Text #7

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1208. Min Act: -0.0001

Data Index: 1222272 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1266. Min Act: -0.0001

Data Index: 889070 (C4 (Web Text))

Max Activating Token Index: 445

Text #9

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1218. Min Act: -0.0001

Data Index: 248247 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1180. Min Act: -0.0001

Data Index: 22944 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1141. Min Act: -0.0001

Data Index: 1331353 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1265728 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1224. Min Act: -0.0001

Data Index: 1077787 (C4 (Web Text))

Max Activating Token Index: 651

Text #14

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1225. Min Act: -0.0001

Data Index: 593342 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1229. Min Act: -0.0001

Data Index: 850841 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1219. Min Act: -0.0001

Data Index: 717166 (C4 (Web Text))

Max Activating Token Index: 476

Text #17

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1179. Min Act: -0.0001

Data Index: 461814 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1256. Min Act: -0.0001

Data Index: 854863 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1302. Min Act: -0.0001

Data Index: 693390 (C4 (Web Text))

Max Activating Token Index: 280