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

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

Neuron 1576 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0517. Min Act: -0.0000

Data Index: 1653188 (Python Code)

Max Activating Token Index: 421

Text #1

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0431. Min Act: -0.0000

Data Index: 918523 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0424. Min Act: -0.0000

Data Index: 911529 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0412. Min Act: -0.0000

Data Index: 1444919 (Python Code)

Max Activating Token Index: 339

Text #4

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0399. Min Act: -0.0000

Data Index: 1485209 (Python Code)

Max Activating Token Index: 973

Text #5

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0380. Min Act: -0.0000

Data Index: 1522087 (Python Code)

Max Activating Token Index: 875

Text #6

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0400. Min Act: -0.0000

Data Index: 1621670 (Python Code)

Max Activating Token Index: 660

Text #7

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0366. Min Act: -0.0000

Data Index: 1471639 (Python Code)

Max Activating Token Index: 737

Text #8

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0351. Min Act: -0.0000

Data Index: 990795 (C4 (Web Text))

Max Activating Token Index: 793

Text #9

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0378. Min Act: -0.0000

Data Index: 1176215 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0356. Min Act: -0.0000

Data Index: 701341 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0344. Min Act: -0.0000

Data Index: 1586481 (Python Code)

Max Activating Token Index: 140

Text #12

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0357. Min Act: -0.0000

Data Index: 1040769 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0326. Min Act: -0.0000

Data Index: 1491167 (Python Code)

Max Activating Token Index: 305

Text #14

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0329. Min Act: -0.0000

Data Index: 1505283 (Python Code)

Max Activating Token Index: 208

Text #15

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0346. Min Act: -0.0000

Data Index: 1636319 (Python Code)

Max Activating Token Index: 446

Text #16

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0349. Min Act: -0.0000

Data Index: 1617884 (Python Code)

Max Activating Token Index: 146

Text #17

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0321. Min Act: -0.0000

Data Index: 1499743 (Python Code)

Max Activating Token Index: 166

Text #18

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0327. Min Act: -0.0000

Data Index: 1617451 (Python Code)

Max Activating Token Index: 383

Text #19

Max Range: 0.0517. Min Range: -0.0517

Max Act: 0.0327. Min Act: -0.0000

Data Index: 817065 (C4 (Web Text))

Max Activating Token Index: 275