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

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

Neuron 2401 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: 1.5653. Min Range: -1.5653

Max Act: 1.5653. Min Act: -0.0000

Data Index: 1375480 (Python Code)

Max Activating Token Index: 474

Text #1

Max Range: 1.5653. Min Range: -1.5653

Max Act: 1.4170. Min Act: -0.0000

Data Index: 1490887 (Python Code)

Max Activating Token Index: 456

Text #2

Max Range: 1.5653. Min Range: -1.5653

Max Act: 1.4117. Min Act: -0.0000

Data Index: 1504499 (Python Code)

Max Activating Token Index: 643

Text #3

Max Range: 1.5653. Min Range: -1.5653

Max Act: 1.2816. Min Act: -0.0000

Data Index: 1397491 (Python Code)

Max Activating Token Index: 490

Text #4

Max Range: 1.5653. Min Range: -1.5653

Max Act: 1.2160. Min Act: -0.0000

Data Index: 1477571 (Python Code)

Max Activating Token Index: 386

Text #5

Max Range: 1.5653. Min Range: -1.5653

Max Act: 1.2032. Min Act: -0.0000

Data Index: 1591966 (Python Code)

Max Activating Token Index: 471

Text #6

Max Range: 1.5653. Min Range: -1.5653

Max Act: 1.1467. Min Act: -0.0000

Data Index: 1584531 (Python Code)

Max Activating Token Index: 404

Text #7

Max Range: 1.5653. Min Range: -1.5653

Max Act: 1.1789. Min Act: -0.0000

Data Index: 1654566 (Python Code)

Max Activating Token Index: 33

Text #8

Max Range: 1.5653. Min Range: -1.5653

Max Act: 1.1236. Min Act: -0.0000

Data Index: 1565476 (Python Code)

Max Activating Token Index: 677

Text #9

Max Range: 1.5653. Min Range: -1.5653

Max Act: 1.1361. Min Act: -0.0000

Data Index: 1516134 (Python Code)

Max Activating Token Index: 193

Text #10

Max Range: 1.5653. Min Range: -1.5653

Max Act: 1.1611. Min Act: -0.0000

Data Index: 1490334 (Python Code)

Max Activating Token Index: 436

Text #11

Max Range: 1.5653. Min Range: -1.5653

Max Act: 1.1831. Min Act: -0.0000

Data Index: 1508627 (Python Code)

Max Activating Token Index: 936

Text #12

Max Range: 1.5653. Min Range: -1.5653

Max Act: 1.1590. Min Act: -0.0000

Data Index: 1572648 (Python Code)

Max Activating Token Index: 817

Text #13

Max Range: 1.5653. Min Range: -1.5653

Max Act: 1.0956. Min Act: -0.0000

Data Index: 1479221 (Python Code)

Max Activating Token Index: 463

Text #14

Max Range: 1.5653. Min Range: -1.5653

Max Act: 1.0983. Min Act: -0.0000

Data Index: 1410384 (Python Code)

Max Activating Token Index: 822

Text #15

Max Range: 1.5653. Min Range: -1.5653

Max Act: 1.0346. Min Act: -0.0000

Data Index: 1585006 (Python Code)

Max Activating Token Index: 596

Text #16

Max Range: 1.5653. Min Range: -1.5653

Max Act: 1.0683. Min Act: -0.0000

Data Index: 1506901 (Python Code)

Max Activating Token Index: 826

Text #17

Max Range: 1.5653. Min Range: -1.5653

Max Act: 1.0905. Min Act: -0.0000

Data Index: 1426985 (Python Code)

Max Activating Token Index: 395

Text #18

Max Range: 1.5653. Min Range: -1.5653

Max Act: 1.0567. Min Act: -0.0000

Data Index: 1422331 (Python Code)

Max Activating Token Index: 676

Text #19

Max Range: 1.5653. Min Range: -1.5653

Max Act: 1.0381. Min Act: -0.0000

Data Index: 1606911 (Python Code)

Max Activating Token Index: 159