Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1371 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1686. Min Act: -0.0001

Data Index: 705955 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1449. Min Act: -0.0002

Data Index: 717822 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1355. Min Act: -0.0002

Data Index: 966322 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1359. Min Act: -0.0002

Data Index: 551351 (C4 (Web Text))

Max Activating Token Index: 778

Text #4

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1357. Min Act: -0.0002

Data Index: 873749 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1302. Min Act: -0.0002

Data Index: 62280 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1318. Min Act: -0.0002

Data Index: 255322 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1337. Min Act: -0.0002

Data Index: 150458 (C4 (Web Text))

Max Activating Token Index: 618

Text #8

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1272. Min Act: -0.0001

Data Index: 1030072 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1268. Min Act: -0.0002

Data Index: 618244 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1286. Min Act: -0.0002

Data Index: 1090311 (C4 (Web Text))

Max Activating Token Index: 1018

Text #11

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1264. Min Act: -0.0002

Data Index: 589376 (C4 (Web Text))

Max Activating Token Index: 974

Text #12

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1302. Min Act: -0.0002

Data Index: 1111290 (C4 (Web Text))

Max Activating Token Index: 133

Text #13

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1241. Min Act: -0.0002

Data Index: 943767 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1281. Min Act: -0.0002

Data Index: 30246 (C4 (Web Text))

Max Activating Token Index: 230

Text #15

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1283. Min Act: -0.0002

Data Index: 665783 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1294. Min Act: -0.0002

Data Index: 38951 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1247. Min Act: -0.0002

Data Index: 836389 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1246. Min Act: -0.0002

Data Index: 600129 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1240. Min Act: -0.0001

Data Index: 1158390 (C4 (Web Text))

Max Activating Token Index: 632