Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1914 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1656. Min Act: -0.0002

Data Index: 631324 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1581. Min Act: -0.0002

Data Index: 829443 (C4 (Web Text))

Max Activating Token Index: 102

Text #2

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1554. Min Act: -0.0002

Data Index: 1527945 (Python Code)

Max Activating Token Index: 787

Text #3

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1439. Min Act: -0.0002

Data Index: 301170 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1417. Min Act: -0.0002

Data Index: 593922 (C4 (Web Text))

Max Activating Token Index: 300

Text #5

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1366. Min Act: -0.0001

Data Index: 511358 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1459. Min Act: -0.0001

Data Index: 1189483 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1417. Min Act: -0.0002

Data Index: 823697 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1325. Min Act: -0.0002

Data Index: 1360598 (Python Code)

Max Activating Token Index: 322

Text #9

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1345. Min Act: -0.0002

Data Index: 1437365 (Python Code)

Max Activating Token Index: 824

Text #10

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1320. Min Act: -0.0002

Data Index: 1430476 (Python Code)

Max Activating Token Index: 844

Text #11

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1348. Min Act: -0.0002

Data Index: 1506759 (Python Code)

Max Activating Token Index: 56

Text #12

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1342. Min Act: -0.0002

Data Index: 647733 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1334. Min Act: -0.0002

Data Index: 1235943 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1328. Min Act: -0.0002

Data Index: 1542589 (Python Code)

Max Activating Token Index: 793

Text #15

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1286. Min Act: -0.0002

Data Index: 1586610 (Python Code)

Max Activating Token Index: 196

Text #16

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1324. Min Act: -0.0002

Data Index: 1241861 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1319. Min Act: -0.0002

Data Index: 497149 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1316. Min Act: -0.0002

Data Index: 330651 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 0.1656. Min Range: -0.1656

Max Act: 0.1270. Min Act: -0.0002

Data Index: 1310073 (C4 (Web Text))

Max Activating Token Index: 392