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

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

Neuron 4404 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: 0.0742. Min Range: -0.0742

Max Act: 0.0722. Min Act: -0.0003

Data Index: 1088430 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0742. Min Act: -0.0003

Data Index: 155536 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0724. Min Act: -0.0002

Data Index: 330639 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0725. Min Act: -0.0003

Data Index: 1036888 (C4 (Web Text))

Max Activating Token Index: 84

Text #4

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0724. Min Act: -0.0003

Data Index: 161700 (C4 (Web Text))

Max Activating Token Index: 482

Text #5

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0651. Min Act: -0.0003

Data Index: 1186108 (C4 (Web Text))

Max Activating Token Index: 248

Text #6

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0690. Min Act: -0.0003

Data Index: 471849 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0711. Min Act: -0.0003

Data Index: 1075344 (C4 (Web Text))

Max Activating Token Index: 90

Text #8

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0671. Min Act: -0.0003

Data Index: 154240 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0645. Min Act: -0.0003

Data Index: 241185 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0669. Min Act: -0.0003

Data Index: 768651 (C4 (Web Text))

Max Activating Token Index: 333

Text #11

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0621. Min Act: -0.0003

Data Index: 378433 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0669. Min Act: -0.0003

Data Index: 1095905 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0645. Min Act: -0.0003

Data Index: 1279426 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0642. Min Act: -0.0003

Data Index: 538585 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0511. Min Act: -0.0003

Data Index: 410276 (C4 (Web Text))

Max Activating Token Index: 234

Text #16

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0679. Min Act: -0.0003

Data Index: 1094690 (C4 (Web Text))

Max Activating Token Index: 448

Text #17

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0590. Min Act: -0.0003

Data Index: 1261647 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0633. Min Act: -0.0003

Data Index: 318002 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0721. Min Act: -0.0003

Data Index: 1337590 (C4 (Web Text))

Max Activating Token Index: 273