Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2532 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1544. Min Range: -0.1544

Max Act: 0.1544. Min Act: -0.0000

Data Index: 52410 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 0.1544. Min Range: -0.1544

Max Act: 0.1526. Min Act: -0.0000

Data Index: 493249 (C4 (Web Text))

Max Activating Token Index: 967

Text #2

Max Range: 0.1544. Min Range: -0.1544

Max Act: 0.1508. Min Act: -0.0000

Data Index: 1224945 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 0.1544. Min Range: -0.1544

Max Act: 0.1419. Min Act: -0.0000

Data Index: 63801 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.1544. Min Range: -0.1544

Max Act: 0.1435. Min Act: -0.0000

Data Index: 572901 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.1544. Min Range: -0.1544

Max Act: 0.1432. Min Act: -0.0000

Data Index: 1563834 (Python Code)

Max Activating Token Index: 756

Text #6

Max Range: 0.1544. Min Range: -0.1544

Max Act: 0.1467. Min Act: 0.0000

Data Index: 493155 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 0.1544. Min Range: -0.1544

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1018468 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.1544. Min Range: -0.1544

Max Act: 0.1257. Min Act: -0.0000

Data Index: 1480140 (Python Code)

Max Activating Token Index: 136

Text #9

Max Range: 0.1544. Min Range: -0.1544

Max Act: 0.1348. Min Act: -0.0000

Data Index: 697503 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.1544. Min Range: -0.1544

Max Act: 0.1281. Min Act: -0.0000

Data Index: 112475 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 0.1544. Min Range: -0.1544

Max Act: 0.1321. Min Act: -0.0000

Data Index: 1101576 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.1544. Min Range: -0.1544

Max Act: 0.1317. Min Act: -0.0000

Data Index: 1348183 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.1544. Min Range: -0.1544

Max Act: 0.1269. Min Act: -0.0000

Data Index: 93432 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.1544. Min Range: -0.1544

Max Act: 0.1317. Min Act: -0.0000

Data Index: 968214 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 0.1544. Min Range: -0.1544

Max Act: 0.1257. Min Act: -0.0000

Data Index: 1043293 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.1544. Min Range: -0.1544

Max Act: 0.1349. Min Act: -0.0000

Data Index: 1264073 (C4 (Web Text))

Max Activating Token Index: 253

Text #17

Max Range: 0.1544. Min Range: -0.1544

Max Act: 0.1288. Min Act: -0.0000

Data Index: 1243660 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 0.1544. Min Range: -0.1544

Max Act: 0.1251. Min Act: -0.0000

Data Index: 132992 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 0.1544. Min Range: -0.1544

Max Act: 0.1292. Min Act: -0.0000

Data Index: 991157 (C4 (Web Text))

Max Activating Token Index: 489