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

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

Neuron 2918 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: 0.1548. Min Range: -0.1548

Max Act: 0.1548. Min Act: -0.0001

Data Index: 806230 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1467. Min Act: -0.0001

Data Index: 1020303 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1365. Min Act: -0.0001

Data Index: 153691 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1289. Min Act: -0.0000

Data Index: 691679 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1258. Min Act: -0.0001

Data Index: 746081 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1253. Min Act: -0.0001

Data Index: 1343709 (C4 (Web Text))

Max Activating Token Index: 677

Text #6

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1282. Min Act: -0.0001

Data Index: 1084075 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1279. Min Act: -0.0001

Data Index: 273333 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1281. Min Act: -0.0001

Data Index: 489964 (C4 (Web Text))

Max Activating Token Index: 913

Text #9

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1302. Min Act: -0.0001

Data Index: 1086938 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1272. Min Act: -0.0001

Data Index: 1212801 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1323. Min Act: -0.0001

Data Index: 81801 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1311. Min Act: -0.0001

Data Index: 1315853 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1273. Min Act: -0.0001

Data Index: 774977 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1259. Min Act: -0.0001

Data Index: 27859 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1224. Min Act: -0.0001

Data Index: 658361 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1227. Min Act: -0.0001

Data Index: 396655 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1163. Min Act: -0.0001

Data Index: 1230014 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1219. Min Act: -0.0001

Data Index: 788019 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.1548. Min Range: -0.1548

Max Act: 0.1178. Min Act: -0.0001

Data Index: 570733 (C4 (Web Text))

Max Activating Token Index: 567