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

Dataset: The Pile

Neuron 4260 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1945649 (The Pile)

Max Activating Token Index: 517

Text #1

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1212433 (The Pile)

Max Activating Token Index: 168

Text #2

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1409. Min Act: -0.0000

Data Index: 1789739 (The Pile)

Max Activating Token Index: 245

Text #3

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1537. Min Act: -0.0000

Data Index: 102794 (The Pile)

Max Activating Token Index: 569

Text #4

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1426. Min Act: -0.0000

Data Index: 859129 (The Pile)

Max Activating Token Index: 914

Text #5

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1407. Min Act: -0.0000

Data Index: 94535 (The Pile)

Max Activating Token Index: 916

Text #6

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1385. Min Act: -0.0000

Data Index: 1557505 (The Pile)

Max Activating Token Index: 308

Text #7

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1360. Min Act: -0.0000

Data Index: 1323472 (The Pile)

Max Activating Token Index: 466

Text #8

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1212. Min Act: -0.0000

Data Index: 1853271 (The Pile)

Max Activating Token Index: 239

Text #9

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1334. Min Act: -0.0000

Data Index: 156654 (The Pile)

Max Activating Token Index: 514

Text #10

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1439. Min Act: -0.0000

Data Index: 196553 (The Pile)

Max Activating Token Index: 860

Text #11

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1280. Min Act: -0.0000

Data Index: 1103371 (The Pile)

Max Activating Token Index: 648

Text #12

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1246. Min Act: -0.0000

Data Index: 411068 (The Pile)

Max Activating Token Index: 985

Text #13

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1334. Min Act: -0.0000

Data Index: 1090259 (The Pile)

Max Activating Token Index: 404

Text #14

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1333. Min Act: -0.0000

Data Index: 961300 (The Pile)

Max Activating Token Index: 816

Text #15

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1322. Min Act: -0.0000

Data Index: 1563613 (The Pile)

Max Activating Token Index: 440

Text #16

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1396370 (The Pile)

Max Activating Token Index: 687

Text #17

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1111358 (The Pile)

Max Activating Token Index: 986

Text #18

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1211. Min Act: -0.0000

Data Index: 1592236 (The Pile)

Max Activating Token Index: 611

Text #19

Max Range: 0.1748. Min Range: -0.1748

Max Act: 0.1397. Min Act: -0.0000

Data Index: 478026 (The Pile)

Max Activating Token Index: 259