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

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

Neuron 4934 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2405. Min Act: -0.0002

Data Index: 1443112 (Python Code)

Max Activating Token Index: 413

Text #1

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2432. Min Act: -0.0002

Data Index: 1569489 (Python Code)

Max Activating Token Index: 266

Text #2

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2352. Min Act: -0.0002

Data Index: 1380550 (Python Code)

Max Activating Token Index: 534

Text #3

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2184. Min Act: -0.0002

Data Index: 1399564 (Python Code)

Max Activating Token Index: 333

Text #4

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2178. Min Act: -0.0002

Data Index: 1651381 (Python Code)

Max Activating Token Index: 643

Text #5

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2173. Min Act: -0.0002

Data Index: 1478365 (Python Code)

Max Activating Token Index: 865

Text #6

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2233. Min Act: -0.0001

Data Index: 1454633 (Python Code)

Max Activating Token Index: 461

Text #7

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2172. Min Act: -0.0002

Data Index: 1423916 (Python Code)

Max Activating Token Index: 921

Text #8

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2129. Min Act: -0.0002

Data Index: 1639544 (Python Code)

Max Activating Token Index: 116

Text #9

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2123. Min Act: -0.0002

Data Index: 1541461 (Python Code)

Max Activating Token Index: 121

Text #10

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2102. Min Act: -0.0002

Data Index: 1387963 (Python Code)

Max Activating Token Index: 110

Text #11

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2086. Min Act: -0.0002

Data Index: 1539234 (Python Code)

Max Activating Token Index: 500

Text #12

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2086. Min Act: -0.0002

Data Index: 1586114 (Python Code)

Max Activating Token Index: 633

Text #13

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2076. Min Act: -0.0002

Data Index: 1656896 (Python Code)

Max Activating Token Index: 107

Text #14

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2065. Min Act: -0.0002

Data Index: 1530038 (Python Code)

Max Activating Token Index: 507

Text #15

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2123. Min Act: -0.0002

Data Index: 1443708 (Python Code)

Max Activating Token Index: 59

Text #16

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.1962. Min Act: -0.0002

Data Index: 1494854 (Python Code)

Max Activating Token Index: 549

Text #17

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2035. Min Act: -0.0002

Data Index: 1634721 (Python Code)

Max Activating Token Index: 243

Text #18

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2018. Min Act: -0.0002

Data Index: 1505416 (Python Code)

Max Activating Token Index: 127

Text #19

Max Range: 0.2432. Min Range: -0.2432

Max Act: 0.2009. Min Act: -0.0002

Data Index: 1559219 (Python Code)

Max Activating Token Index: 406