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

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

Neuron 4719 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: 4.8025. Min Range: -4.8025

Max Act: 4.8025. Min Act: -0.0000

Data Index: 537595 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 4.8025. Min Range: -4.8025

Max Act: 4.4914. Min Act: -0.0000

Data Index: 1309036 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 4.8025. Min Range: -4.8025

Max Act: 4.2821. Min Act: -0.0000

Data Index: 30992 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 4.8025. Min Range: -4.8025

Max Act: 4.7818. Min Act: -0.0000

Data Index: 534343 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 4.8025. Min Range: -4.8025

Max Act: 4.5502. Min Act: -0.0000

Data Index: 304410 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 4.8025. Min Range: -4.8025

Max Act: 4.6296. Min Act: -0.0000

Data Index: 317053 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 4.8025. Min Range: -4.8025

Max Act: 4.4724. Min Act: -0.0000

Data Index: 1180517 (C4 (Web Text))

Max Activating Token Index: 248

Text #7

Max Range: 4.8025. Min Range: -4.8025

Max Act: 4.4559. Min Act: -0.0000

Data Index: 462279 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 4.8025. Min Range: -4.8025

Max Act: 4.1515. Min Act: -0.0000

Data Index: 1122642 (C4 (Web Text))

Max Activating Token Index: 109

Text #9

Max Range: 4.8025. Min Range: -4.8025

Max Act: 4.3028. Min Act: -0.0000

Data Index: 863268 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 4.8025. Min Range: -4.8025

Max Act: 4.1141. Min Act: -0.0000

Data Index: 947329 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 4.8025. Min Range: -4.8025

Max Act: 4.2512. Min Act: -0.0000

Data Index: 459830 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 4.8025. Min Range: -4.8025

Max Act: 4.0971. Min Act: -0.0000

Data Index: 635041 (C4 (Web Text))

Max Activating Token Index: 784

Text #13

Max Range: 4.8025. Min Range: -4.8025

Max Act: 4.4076. Min Act: -0.0000

Data Index: 1184501 (C4 (Web Text))

Max Activating Token Index: 587

Text #14

Max Range: 4.8025. Min Range: -4.8025

Max Act: 4.0650. Min Act: -0.0000

Data Index: 1328325 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 4.8025. Min Range: -4.8025

Max Act: 4.2398. Min Act: -0.0000

Data Index: 1232690 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 4.8025. Min Range: -4.8025

Max Act: 4.1947. Min Act: -0.0000

Data Index: 984709 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 4.8025. Min Range: -4.8025

Max Act: 4.2145. Min Act: -0.0000

Data Index: 940973 (C4 (Web Text))

Max Activating Token Index: 616

Text #18

Max Range: 4.8025. Min Range: -4.8025

Max Act: 4.0212. Min Act: -0.0000

Data Index: 1195976 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 4.8025. Min Range: -4.8025

Max Act: 4.1477. Min Act: -0.0000

Data Index: 453792 (C4 (Web Text))

Max Activating Token Index: 90