Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5700 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.1926. Min Act: -0.0002

Data Index: 1321707 (C4 (Web Text))

Max Activating Token Index: 405

Text #1

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.0498. Min Act: -0.0002

Data Index: 400967 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.0442. Min Act: -0.0002

Data Index: 1295330 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.0424. Min Act: -0.0002

Data Index: 645157 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.0399. Min Act: -0.0002

Data Index: 811897 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.0369. Min Act: -0.0002

Data Index: 1053470 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.0356. Min Act: -0.0002

Data Index: 1081800 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.0301. Min Act: -0.0002

Data Index: 263468 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.0329. Min Act: -0.0002

Data Index: 312322 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.0297. Min Act: -0.0002

Data Index: 67776 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1198513 (C4 (Web Text))

Max Activating Token Index: 29

Text #11

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.0285. Min Act: -0.0002

Data Index: 348300 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.0260. Min Act: -0.0002

Data Index: 280366 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.0284. Min Act: -0.0002

Data Index: 702863 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.0283. Min Act: -0.0002

Data Index: 201088 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.0270. Min Act: -0.0002

Data Index: 920850 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1121383 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.0268. Min Act: -0.0002

Data Index: 13123 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.0258. Min Act: -0.0002

Data Index: 1093444 (C4 (Web Text))

Max Activating Token Index: 546

Text #19

Max Range: 0.1926. Min Range: -0.1926

Max Act: 0.0249. Min Act: -0.0002

Data Index: 25160 (C4 (Web Text))

Max Activating Token Index: 945