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

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

Neuron 4951 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1576. Min Act: -0.0002

Data Index: 247153 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1586. Min Act: -0.0002

Data Index: 927213 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1511. Min Act: -0.0002

Data Index: 149952 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1480. Min Act: -0.0003

Data Index: 23524 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1383. Min Act: -0.0002

Data Index: 1032112 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1341. Min Act: -0.0002

Data Index: 1214435 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1339. Min Act: -0.0003

Data Index: 966903 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1309. Min Act: -0.0003

Data Index: 891665 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1335. Min Act: -0.0002

Data Index: 516717 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1290. Min Act: -0.0002

Data Index: 627171 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1273. Min Act: -0.0002

Data Index: 400588 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1262. Min Act: -0.0003

Data Index: 320473 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1302. Min Act: -0.0002

Data Index: 337220 (C4 (Web Text))

Max Activating Token Index: 856

Text #13

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1245. Min Act: -0.0002

Data Index: 495368 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1229. Min Act: -0.0002

Data Index: 1314508 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1224. Min Act: -0.0002

Data Index: 863386 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1222. Min Act: -0.0003

Data Index: 1227234 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1226. Min Act: -0.0003

Data Index: 321324 (C4 (Web Text))

Max Activating Token Index: 198

Text #18

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1217. Min Act: -0.0002

Data Index: 681547 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 0.1586. Min Range: -0.1586

Max Act: 0.1201. Min Act: -0.0002

Data Index: 1011772 (C4 (Web Text))

Max Activating Token Index: 575