Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4479 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2360. Min Act: -0.0000

Data Index: 1373173 (Python Code)

Max Activating Token Index: 639

Text #1

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2059. Min Act: -0.0000

Data Index: 294024 (C4 (Web Text))

Max Activating Token Index: 951

Text #2

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1796. Min Act: -0.0000

Data Index: 582593 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1628. Min Act: -0.0000

Data Index: 1587769 (Python Code)

Max Activating Token Index: 830

Text #4

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1631. Min Act: -0.0000

Data Index: 609609 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1047143 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1485. Min Act: -0.0000

Data Index: 748892 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1617. Min Act: -0.0000

Data Index: 407429 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1470. Min Act: -0.0000

Data Index: 238654 (C4 (Web Text))

Max Activating Token Index: 402

Text #9

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1401. Min Act: -0.0000

Data Index: 1417354 (Python Code)

Max Activating Token Index: 634

Text #10

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1484. Min Act: -0.0000

Data Index: 94978 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1442. Min Act: -0.0000

Data Index: 1014436 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1398. Min Act: -0.0000

Data Index: 1418207 (Python Code)

Max Activating Token Index: 144

Text #13

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1355. Min Act: 0.0000

Data Index: 412979 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1346. Min Act: -0.0000

Data Index: 1192257 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1334. Min Act: -0.0000

Data Index: 1541283 (Python Code)

Max Activating Token Index: 357

Text #16

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1345. Min Act: -0.0000

Data Index: 684799 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1242. Min Act: -0.0000

Data Index: 785787 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1314. Min Act: -0.0000

Data Index: 571241 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1306. Min Act: -0.0000

Data Index: 1536197 (Python Code)

Max Activating Token Index: 104