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

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

Neuron 4701 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.2295. Min Act: -0.0000

Data Index: 207457 (C4 (Web Text))

Max Activating Token Index: 411

Text #1

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.2204. Min Act: -0.0000

Data Index: 1338761 (C4 (Web Text))

Max Activating Token Index: 797

Text #2

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1794. Min Act: -0.0000

Data Index: 657823 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1526299 (Python Code)

Max Activating Token Index: 981

Text #4

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1723. Min Act: -0.0000

Data Index: 574014 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1725. Min Act: -0.0000

Data Index: 1540997 (Python Code)

Max Activating Token Index: 390

Text #6

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1592. Min Act: 0.0001

Data Index: 416319 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1780. Min Act: -0.0000

Data Index: 129116 (C4 (Web Text))

Max Activating Token Index: 680

Text #8

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1611. Min Act: -0.0000

Data Index: 915052 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1590. Min Act: -0.0000

Data Index: 1079650 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1495. Min Act: -0.0000

Data Index: 602999 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1558. Min Act: -0.0000

Data Index: 45516 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1480. Min Act: -0.0000

Data Index: 1550824 (Python Code)

Max Activating Token Index: 865

Text #13

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1608. Min Act: -0.0000

Data Index: 1199150 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1479. Min Act: -0.0000

Data Index: 1367071 (Python Code)

Max Activating Token Index: 843

Text #15

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1488. Min Act: -0.0000

Data Index: 585056 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1488. Min Act: -0.0000

Data Index: 813196 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1467. Min Act: -0.0000

Data Index: 1238338 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1439. Min Act: -0.0000

Data Index: 1271645 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.2295. Min Range: -0.2295

Max Act: 0.1415. Min Act: -0.0000

Data Index: 925828 (C4 (Web Text))

Max Activating Token Index: 892