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

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

Neuron 2598 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: 0.1455. Min Range: -0.1455

Max Act: 0.1455. Min Act: -0.0001

Data Index: 608155 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1405. Min Act: -0.0001

Data Index: 716489 (C4 (Web Text))

Max Activating Token Index: 448

Text #2

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1281. Min Act: -0.0001

Data Index: 424128 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1285. Min Act: -0.0001

Data Index: 49758 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1264. Min Act: -0.0001

Data Index: 219187 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1425. Min Act: -0.0001

Data Index: 1085153 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1265. Min Act: -0.0001

Data Index: 652035 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1220. Min Act: -0.0001

Data Index: 402277 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1231. Min Act: -0.0001

Data Index: 1028386 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1300. Min Act: -0.0001

Data Index: 1016210 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1241. Min Act: -0.0001

Data Index: 1047807 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1161. Min Act: -0.0001

Data Index: 552525 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1224. Min Act: -0.0001

Data Index: 1450465 (Python Code)

Max Activating Token Index: 72

Text #13

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1217. Min Act: -0.0001

Data Index: 252761 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1206. Min Act: -0.0001

Data Index: 270213 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1333. Min Act: -0.0001

Data Index: 156605 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1234. Min Act: -0.0001

Data Index: 1112891 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1144. Min Act: -0.0001

Data Index: 102197 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1188. Min Act: -0.0001

Data Index: 579989 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 0.1455. Min Range: -0.1455

Max Act: 0.1070. Min Act: -0.0001

Data Index: 517766 (C4 (Web Text))

Max Activating Token Index: 938