Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2223 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.5439. Min Act: -0.0002

Data Index: 308243 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.5807. Min Act: -0.0002

Data Index: 627712 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.5629. Min Act: -0.0002

Data Index: 667947 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.5772. Min Act: -0.0001

Data Index: 1022161 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.5351. Min Act: -0.0002

Data Index: 569953 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.5549. Min Act: -0.0002

Data Index: 478445 (C4 (Web Text))

Max Activating Token Index: 766

Text #6

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.4997. Min Act: -0.0001

Data Index: 887130 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.5684. Min Act: -0.0002

Data Index: 419868 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.5468. Min Act: -0.0002

Data Index: 1111181 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.5301. Min Act: -0.0001

Data Index: 380910 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.5135. Min Act: -0.0002

Data Index: 340701 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.5588. Min Act: -0.0001

Data Index: 1224812 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.5373. Min Act: -0.0001

Data Index: 597182 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.5348. Min Act: -0.0001

Data Index: 376394 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.5491. Min Act: -0.0001

Data Index: 260740 (C4 (Web Text))

Max Activating Token Index: 390

Text #15

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.5121. Min Act: -0.0002

Data Index: 976057 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.5157. Min Act: -0.0002

Data Index: 1169106 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.5246. Min Act: -0.0002

Data Index: 182344 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.5230. Min Act: -0.0001

Data Index: 570515 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.5807. Min Range: -0.5807

Max Act: 0.5061. Min Act: -0.0001

Data Index: 213509 (C4 (Web Text))

Max Activating Token Index: 221