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

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

Neuron 4462 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4708. Min Range: -2.4708

Max Act: 2.3461. Min Act: 0.0000

Data Index: 1615523 (Python Code)

Max Activating Token Index: 551

Text #1

Max Range: 2.4708. Min Range: -2.4708

Max Act: 2.4708. Min Act: 0.0000

Data Index: 1373239 (Python Code)

Max Activating Token Index: 134

Text #2

Max Range: 2.4708. Min Range: -2.4708

Max Act: 2.3634. Min Act: -0.0000

Data Index: 1484441 (Python Code)

Max Activating Token Index: 515

Text #3

Max Range: 2.4708. Min Range: -2.4708

Max Act: 2.3376. Min Act: 0.0000

Data Index: 1614014 (Python Code)

Max Activating Token Index: 182

Text #4

Max Range: 2.4708. Min Range: -2.4708

Max Act: 2.1681. Min Act: 0.0000

Data Index: 1499915 (Python Code)

Max Activating Token Index: 715

Text #5

Max Range: 2.4708. Min Range: -2.4708

Max Act: 2.3679. Min Act: 0.0000

Data Index: 1460350 (Python Code)

Max Activating Token Index: 518

Text #6

Max Range: 2.4708. Min Range: -2.4708

Max Act: 2.2222. Min Act: -0.0000

Data Index: 1446305 (Python Code)

Max Activating Token Index: 45

Text #7

Max Range: 2.4708. Min Range: -2.4708

Max Act: 2.0871. Min Act: 0.0000

Data Index: 1638282 (Python Code)

Max Activating Token Index: 881

Text #8

Max Range: 2.4708. Min Range: -2.4708

Max Act: 2.2462. Min Act: 0.0000

Data Index: 1530689 (Python Code)

Max Activating Token Index: 700

Text #9

Max Range: 2.4708. Min Range: -2.4708

Max Act: 2.0333. Min Act: -0.0000

Data Index: 1577459 (Python Code)

Max Activating Token Index: 933

Text #10

Max Range: 2.4708. Min Range: -2.4708

Max Act: 2.1213. Min Act: 0.0000

Data Index: 1381045 (Python Code)

Max Activating Token Index: 844

Text #11

Max Range: 2.4708. Min Range: -2.4708

Max Act: 1.8263. Min Act: -0.0000

Data Index: 1510623 (Python Code)

Max Activating Token Index: 792

Text #12

Max Range: 2.4708. Min Range: -2.4708

Max Act: 1.9946. Min Act: -0.0000

Data Index: 1366426 (Python Code)

Max Activating Token Index: 807

Text #13

Max Range: 2.4708. Min Range: -2.4708

Max Act: 1.7816. Min Act: -0.0000

Data Index: 1466174 (Python Code)

Max Activating Token Index: 524

Text #14

Max Range: 2.4708. Min Range: -2.4708

Max Act: 1.7725. Min Act: 0.0000

Data Index: 1364635 (Python Code)

Max Activating Token Index: 154

Text #15

Max Range: 2.4708. Min Range: -2.4708

Max Act: 1.8405. Min Act: -0.0001

Data Index: 1482285 (Python Code)

Max Activating Token Index: 436

Text #16

Max Range: 2.4708. Min Range: -2.4708

Max Act: 1.7335. Min Act: -0.0000

Data Index: 1583363 (Python Code)

Max Activating Token Index: 441

Text #17

Max Range: 2.4708. Min Range: -2.4708

Max Act: 1.6940. Min Act: -0.0000

Data Index: 1409046 (Python Code)

Max Activating Token Index: 415

Text #18

Max Range: 2.4708. Min Range: -2.4708

Max Act: 1.6222. Min Act: -0.0000

Data Index: 1646474 (Python Code)

Max Activating Token Index: 842

Text #19

Max Range: 2.4708. Min Range: -2.4708

Max Act: 1.5928. Min Act: -0.0000

Data Index: 1654058 (Python Code)

Max Activating Token Index: 432