Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 614 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1601. Min Act: -0.0003

Data Index: 398008 (C4 (Web Text))

Max Activating Token Index: 923

Text #1

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1403. Min Act: -0.0003

Data Index: 496186 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1457. Min Act: -0.0003

Data Index: 948041 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1376. Min Act: -0.0002

Data Index: 1145901 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1380. Min Act: -0.0003

Data Index: 1303787 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1344. Min Act: -0.0003

Data Index: 392206 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1362. Min Act: -0.0003

Data Index: 87816 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1364. Min Act: -0.0003

Data Index: 313857 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1279. Min Act: -0.0003

Data Index: 1302999 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1249. Min Act: -0.0003

Data Index: 1315882 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1283. Min Act: -0.0003

Data Index: 229661 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1247. Min Act: -0.0004

Data Index: 1268559 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1323. Min Act: -0.0003

Data Index: 1082270 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1325. Min Act: -0.0003

Data Index: 233747 (C4 (Web Text))

Max Activating Token Index: 622

Text #14

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1292. Min Act: -0.0003

Data Index: 766016 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1237. Min Act: -0.0003

Data Index: 107951 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1227. Min Act: -0.0003

Data Index: 1068508 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1256. Min Act: -0.0003

Data Index: 670144 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1178. Min Act: -0.0003

Data Index: 937708 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.1601. Min Range: -0.1601

Max Act: 0.1251. Min Act: -0.0003

Data Index: 712865 (C4 (Web Text))

Max Activating Token Index: 479