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

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

Neuron 2768 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: 0.1461. Min Range: -0.1461

Max Act: 0.1449. Min Act: -0.0002

Data Index: 1273797 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1213. Min Act: -0.0002

Data Index: 1293429 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1383. Min Act: -0.0002

Data Index: 384312 (C4 (Web Text))

Max Activating Token Index: 634

Text #3

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1461. Min Act: -0.0002

Data Index: 5225 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1311. Min Act: -0.0002

Data Index: 145358 (C4 (Web Text))

Max Activating Token Index: 228

Text #5

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1305. Min Act: -0.0002

Data Index: 681853 (C4 (Web Text))

Max Activating Token Index: 457

Text #6

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1431. Min Act: -0.0002

Data Index: 159985 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1245. Min Act: -0.0002

Data Index: 1324313 (C4 (Web Text))

Max Activating Token Index: 321

Text #8

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1268. Min Act: -0.0002

Data Index: 157432 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1234. Min Act: -0.0002

Data Index: 285288 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1256. Min Act: -0.0002

Data Index: 450483 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1177. Min Act: -0.0002

Data Index: 867635 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1302. Min Act: -0.0002

Data Index: 119416 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1244. Min Act: -0.0002

Data Index: 849460 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1287. Min Act: -0.0002

Data Index: 10533 (C4 (Web Text))

Max Activating Token Index: 97

Text #15

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1353. Min Act: -0.0002

Data Index: 595181 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1116. Min Act: -0.0002

Data Index: 333780 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1427. Min Act: -0.0002

Data Index: 568431 (C4 (Web Text))

Max Activating Token Index: 309

Text #18

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1273. Min Act: -0.0002

Data Index: 744406 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 0.1461. Min Range: -0.1461

Max Act: 0.1222. Min Act: -0.0002

Data Index: 961631 (C4 (Web Text))

Max Activating Token Index: 392