Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2150 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1734. Min Act: -0.0001

Data Index: 607258 (C4 (Web Text))

Max Activating Token Index: 567

Text #1

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1447. Min Act: -0.0001

Data Index: 839026 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1364. Min Act: -0.0001

Data Index: 778719 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1346. Min Act: -0.0001

Data Index: 1137465 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1353. Min Act: -0.0001

Data Index: 1200506 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1290. Min Act: -0.0001

Data Index: 1203423 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1309. Min Act: -0.0001

Data Index: 888250 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1368. Min Act: -0.0001

Data Index: 560800 (C4 (Web Text))

Max Activating Token Index: 489

Text #8

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1349. Min Act: -0.0001

Data Index: 774486 (C4 (Web Text))

Max Activating Token Index: 815

Text #9

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1306. Min Act: -0.0001

Data Index: 282041 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1265. Min Act: -0.0001

Data Index: 852438 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1376. Min Act: -0.0001

Data Index: 322149 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1335. Min Act: -0.0001

Data Index: 552026 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1339. Min Act: -0.0001

Data Index: 51914 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1283. Min Act: -0.0001

Data Index: 524854 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1178. Min Act: -0.0001

Data Index: 1112074 (C4 (Web Text))

Max Activating Token Index: 870

Text #16

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1214. Min Act: -0.0001

Data Index: 754134 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1265. Min Act: -0.0001

Data Index: 627083 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1335. Min Act: -0.0001

Data Index: 1191646 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 0.1734. Min Range: -0.1734

Max Act: 0.1109. Min Act: -0.0001

Data Index: 754668 (C4 (Web Text))

Max Activating Token Index: 802