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

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

Neuron 4157 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0828. Min Act: -0.0002

Data Index: 200337 (C4 (Web Text))

Max Activating Token Index: 612

Text #1

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0678. Min Act: -0.0002

Data Index: 887911 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0577. Min Act: -0.0002

Data Index: 63812 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0453. Min Act: -0.0002

Data Index: 481932 (C4 (Web Text))

Max Activating Token Index: 709

Text #4

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0525. Min Act: -0.0002

Data Index: 1034395 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0499. Min Act: -0.0002

Data Index: 643062 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1328242 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0360. Min Act: -0.0002

Data Index: 147191 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1182383 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0449. Min Act: -0.0002

Data Index: 985334 (C4 (Web Text))

Max Activating Token Index: 420

Text #10

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0415. Min Act: -0.0002

Data Index: 678010 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1109976 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0429. Min Act: -0.0002

Data Index: 607183 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0389. Min Act: -0.0002

Data Index: 608589 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1351833 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0469. Min Act: -0.0002

Data Index: 652263 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0393. Min Act: -0.0002

Data Index: 644464 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0401. Min Act: -0.0002

Data Index: 207718 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0408. Min Act: -0.0002

Data Index: 918595 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 0.0828. Min Range: -0.0828

Max Act: 0.0396. Min Act: -0.0002

Data Index: 181804 (C4 (Web Text))

Max Activating Token Index: 545