Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1366 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0642. Min Act: -0.0003

Data Index: 31394 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0663. Min Act: -0.0003

Data Index: 1225774 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1334169 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0649. Min Act: -0.0003

Data Index: 1158684 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0625. Min Act: -0.0003

Data Index: 990323 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0625. Min Act: -0.0002

Data Index: 901683 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0621. Min Act: -0.0003

Data Index: 910120 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0607. Min Act: -0.0003

Data Index: 71159 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0609. Min Act: -0.0001

Data Index: 377241 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0601. Min Act: -0.0003

Data Index: 100156 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0599. Min Act: -0.0002

Data Index: 691516 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0591. Min Act: -0.0003

Data Index: 701533 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0597. Min Act: -0.0002

Data Index: 127215 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0600. Min Act: -0.0003

Data Index: 917674 (C4 (Web Text))

Max Activating Token Index: 269

Text #14

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0584. Min Act: -0.0002

Data Index: 192294 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0580. Min Act: 0.0000

Data Index: 791117 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0578. Min Act: -0.0003

Data Index: 109827 (C4 (Web Text))

Max Activating Token Index: 740

Text #17

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0571. Min Act: -0.0001

Data Index: 1127677 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0582. Min Act: -0.0003

Data Index: 1358438 (C4 (Web Text))

Max Activating Token Index: 302

Text #19

Max Range: 0.0663. Min Range: -0.0663

Max Act: 0.0567. Min Act: -0.0000

Data Index: 766490 (C4 (Web Text))

Max Activating Token Index: 551