Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3356 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1695. Min Act: -0.0001

Data Index: 112117 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1510. Min Act: -0.0001

Data Index: 867748 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1505. Min Act: -0.0001

Data Index: 180249 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1286. Min Act: -0.0001

Data Index: 594046 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1319. Min Act: -0.0001

Data Index: 1266367 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1260. Min Act: -0.0001

Data Index: 608991 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1216. Min Act: -0.0001

Data Index: 1325126 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1143. Min Act: -0.0001

Data Index: 1116822 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1270. Min Act: -0.0001

Data Index: 1239062 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1225. Min Act: -0.0001

Data Index: 862232 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1271. Min Act: -0.0001

Data Index: 1082888 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1291. Min Act: -0.0001

Data Index: 723445 (C4 (Web Text))

Max Activating Token Index: 767

Text #12

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1202. Min Act: -0.0001

Data Index: 627505 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1329. Min Act: -0.0001

Data Index: 210804 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1244. Min Act: -0.0001

Data Index: 878639 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1220. Min Act: -0.0001

Data Index: 396387 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1219. Min Act: -0.0001

Data Index: 1180945 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1128. Min Act: -0.0001

Data Index: 831829 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1163. Min Act: -0.0001

Data Index: 616967 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 0.1695. Min Range: -0.1695

Max Act: 0.1258. Min Act: -0.0001

Data Index: 263951 (C4 (Web Text))

Max Activating Token Index: 134