Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1142 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1639. Min Act: -0.0003

Data Index: 1073318 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1631. Min Act: -0.0003

Data Index: 1269291 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1604. Min Act: -0.0003

Data Index: 77629 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1586. Min Act: -0.0004

Data Index: 1089844 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1604. Min Act: -0.0003

Data Index: 1113501 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1569. Min Act: -0.0003

Data Index: 553776 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1586. Min Act: -0.0003

Data Index: 953564 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1564. Min Act: -0.0003

Data Index: 367526 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1510. Min Act: -0.0003

Data Index: 278436 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1507. Min Act: -0.0004

Data Index: 1207418 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1413. Min Act: -0.0003

Data Index: 556676 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1477. Min Act: -0.0003

Data Index: 1118706 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1409. Min Act: -0.0003

Data Index: 695275 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1420. Min Act: -0.0003

Data Index: 111042 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1427. Min Act: -0.0003

Data Index: 627775 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1381. Min Act: -0.0004

Data Index: 1000178 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1326. Min Act: -0.0004

Data Index: 779050 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1293. Min Act: -0.0003

Data Index: 223344 (C4 (Web Text))

Max Activating Token Index: 202

Text #18

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1222. Min Act: -0.0003

Data Index: 318441 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 0.1639. Min Range: -0.1639

Max Act: 0.1409. Min Act: -0.0003

Data Index: 464397 (C4 (Web Text))

Max Activating Token Index: 964