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

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

Neuron 3207 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: 0.0744. Min Range: -0.0744

Max Act: 0.0744. Min Act: -0.0003

Data Index: 214210 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0621. Min Act: -0.0003

Data Index: 504046 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0589. Min Act: -0.0003

Data Index: 1032305 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0611. Min Act: -0.0003

Data Index: 958627 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0614. Min Act: -0.0003

Data Index: 533665 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0540. Min Act: -0.0003

Data Index: 1022693 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0515. Min Act: -0.0003

Data Index: 703278 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0447. Min Act: -0.0003

Data Index: 593235 (C4 (Web Text))

Max Activating Token Index: 601

Text #8

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1155004 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0499. Min Act: -0.0003

Data Index: 707235 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0471. Min Act: -0.0003

Data Index: 902052 (C4 (Web Text))

Max Activating Token Index: 563

Text #11

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0486. Min Act: -0.0003

Data Index: 872956 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0473. Min Act: -0.0003

Data Index: 1046475 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0474. Min Act: -0.0003

Data Index: 547315 (C4 (Web Text))

Max Activating Token Index: 380

Text #14

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0483. Min Act: -0.0003

Data Index: 236638 (C4 (Web Text))

Max Activating Token Index: 886

Text #15

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0453. Min Act: -0.0003

Data Index: 1254589 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0443. Min Act: -0.0003

Data Index: 680945 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0475. Min Act: -0.0002

Data Index: 631688 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0423. Min Act: -0.0003

Data Index: 1006733 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.0744. Min Range: -0.0744

Max Act: 0.0443. Min Act: -0.0003

Data Index: 949450 (C4 (Web Text))

Max Activating Token Index: 424