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

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

Neuron 1670 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0490. Min Act: -0.0003

Data Index: 61751 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0424. Min Act: -0.0003

Data Index: 780669 (C4 (Web Text))

Max Activating Token Index: 743

Text #2

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0413. Min Act: -0.0003

Data Index: 582114 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0374. Min Act: -0.0003

Data Index: 856491 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0368. Min Act: -0.0003

Data Index: 1296328 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0338. Min Act: -0.0003

Data Index: 883481 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0323. Min Act: -0.0003

Data Index: 595255 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0321. Min Act: -0.0003

Data Index: 760356 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0310. Min Act: -0.0003

Data Index: 1299879 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0341. Min Act: -0.0003

Data Index: 295181 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1022216 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1024587 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0284. Min Act: -0.0003

Data Index: 506870 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0325. Min Act: -0.0003

Data Index: 692418 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0276. Min Act: -0.0003

Data Index: 1345462 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0286. Min Act: -0.0003

Data Index: 803666 (C4 (Web Text))

Max Activating Token Index: 747

Text #16

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1315615 (C4 (Web Text))

Max Activating Token Index: 33

Text #17

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0298. Min Act: -0.0003

Data Index: 1275171 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0297. Min Act: -0.0003

Data Index: 820228 (C4 (Web Text))

Max Activating Token Index: 664

Text #19

Max Range: 0.0490. Min Range: -0.0490

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1030751 (C4 (Web Text))

Max Activating Token Index: 619