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

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

Neuron 1832 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.4782. Min Act: -0.0000

Data Index: 1190902 (C4 (Web Text))

Max Activating Token Index: 999

Text #1

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.3589. Min Act: -0.0000

Data Index: 337599 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.5537. Min Act: -0.0000

Data Index: 79072 (C4 (Web Text))

Max Activating Token Index: 721

Text #3

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.2093. Min Act: -0.0000

Data Index: 921329 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.2874. Min Act: -0.0000

Data Index: 840926 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.2205. Min Act: -0.0000

Data Index: 1534769 (Python Code)

Max Activating Token Index: 764

Text #6

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.2424. Min Act: -0.0000

Data Index: 1520194 (Python Code)

Max Activating Token Index: 58

Text #7

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.1122. Min Act: -0.0000

Data Index: 1450084 (Python Code)

Max Activating Token Index: 123

Text #8

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.2193. Min Act: -0.0000

Data Index: 712788 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.1643. Min Act: -0.0000

Data Index: 691134 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.1671. Min Act: -0.0000

Data Index: 284613 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.1247. Min Act: -0.0000

Data Index: 828190 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.2284. Min Act: -0.0000

Data Index: 1123378 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.1722. Min Act: -0.0000

Data Index: 866989 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.1670. Min Act: -0.0000

Data Index: 342559 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.0248. Min Act: -0.0000

Data Index: 1651449 (Python Code)

Max Activating Token Index: 730

Text #16

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.3194. Min Act: -0.0000

Data Index: 795652 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.1583. Min Act: -0.0000

Data Index: 1635280 (Python Code)

Max Activating Token Index: 461

Text #18

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.0650. Min Act: -0.0000

Data Index: 1501188 (Python Code)

Max Activating Token Index: 477

Text #19

Max Range: 1.5537. Min Range: -1.5537

Max Act: 1.0895. Min Act: -0.0000

Data Index: 1471893 (Python Code)

Max Activating Token Index: 62