Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1452 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1567. Min Act: -0.0001

Data Index: 431488 (C4 (Web Text))

Max Activating Token Index: 918

Text #1

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1725. Min Act: -0.0001

Data Index: 1456392 (Python Code)

Max Activating Token Index: 499

Text #2

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1545. Min Act: -0.0000

Data Index: 947771 (C4 (Web Text))

Max Activating Token Index: 590

Text #3

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1669. Min Act: -0.0000

Data Index: 463440 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1502. Min Act: -0.0001

Data Index: 1409785 (Python Code)

Max Activating Token Index: 558

Text #5

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1485. Min Act: -0.0001

Data Index: 483064 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1652. Min Act: -0.0000

Data Index: 492838 (C4 (Web Text))

Max Activating Token Index: 816

Text #7

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1721. Min Act: -0.0001

Data Index: 515792 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1347641 (C4 (Web Text))

Max Activating Token Index: 848

Text #9

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1429. Min Act: -0.0001

Data Index: 1626015 (Python Code)

Max Activating Token Index: 913

Text #10

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1476. Min Act: -0.0000

Data Index: 1091783 (C4 (Web Text))

Max Activating Token Index: 992

Text #11

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1149276 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1362. Min Act: -0.0001

Data Index: 1598446 (Python Code)

Max Activating Token Index: 475

Text #13

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1337. Min Act: -0.0000

Data Index: 678787 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1368. Min Act: -0.0001

Data Index: 1518872 (Python Code)

Max Activating Token Index: 58

Text #15

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1366. Min Act: -0.0001

Data Index: 319937 (C4 (Web Text))

Max Activating Token Index: 403

Text #16

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1335. Min Act: -0.0000

Data Index: 50405 (C4 (Web Text))

Max Activating Token Index: 363

Text #17

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1251. Min Act: -0.0000

Data Index: 845708 (C4 (Web Text))

Max Activating Token Index: 795

Text #18

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1263. Min Act: -0.0000

Data Index: 58223 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 0.1725. Min Range: -0.1725

Max Act: 0.1324. Min Act: -0.0000

Data Index: 481378 (C4 (Web Text))

Max Activating Token Index: 926