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

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

Neuron 4558 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1677. Min Act: -0.0002

Data Index: 914330 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1602. Min Act: -0.0002

Data Index: 130994 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1301. Min Act: -0.0002

Data Index: 1310499 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1396. Min Act: -0.0002

Data Index: 670172 (C4 (Web Text))

Max Activating Token Index: 883

Text #4

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1362. Min Act: -0.0002

Data Index: 1012548 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1401. Min Act: -0.0002

Data Index: 501119 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1310. Min Act: -0.0002

Data Index: 622674 (C4 (Web Text))

Max Activating Token Index: 280

Text #7

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1286. Min Act: -0.0002

Data Index: 947871 (C4 (Web Text))

Max Activating Token Index: 28

Text #8

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1271. Min Act: -0.0002

Data Index: 108934 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1429. Min Act: -0.0002

Data Index: 72367 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1245. Min Act: -0.0002

Data Index: 378841 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1312. Min Act: -0.0002

Data Index: 1198628 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1300. Min Act: -0.0002

Data Index: 1046849 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1243. Min Act: -0.0002

Data Index: 1293309 (C4 (Web Text))

Max Activating Token Index: 86

Text #14

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1272. Min Act: -0.0002

Data Index: 774901 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1238. Min Act: -0.0002

Data Index: 892564 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1290. Min Act: -0.0002

Data Index: 191067 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1218. Min Act: -0.0002

Data Index: 924922 (C4 (Web Text))

Max Activating Token Index: 269

Text #18

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1187. Min Act: -0.0002

Data Index: 693511 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1257. Min Act: -0.0002

Data Index: 943642 (C4 (Web Text))

Max Activating Token Index: 346