Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1725 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0505. Min Act: -0.0002

Data Index: 1518269 (Python Code)

Max Activating Token Index: 879

Text #1

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1604443 (Python Code)

Max Activating Token Index: 676

Text #2

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0454. Min Act: -0.0002

Data Index: 540791 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0444. Min Act: -0.0002

Data Index: 371460 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1351802 (C4 (Web Text))

Max Activating Token Index: 358

Text #5

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0441. Min Act: -0.0002

Data Index: 287799 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1478783 (Python Code)

Max Activating Token Index: 434

Text #7

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0425. Min Act: -0.0002

Data Index: 269058 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1140694 (C4 (Web Text))

Max Activating Token Index: 415

Text #9

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0397. Min Act: -0.0002

Data Index: 440809 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0415. Min Act: -0.0002

Data Index: 391593 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0406. Min Act: -0.0002

Data Index: 836551 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0397. Min Act: -0.0002

Data Index: 342201 (C4 (Web Text))

Max Activating Token Index: 385

Text #13

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0396. Min Act: -0.0002

Data Index: 1144025 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1225661 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0399. Min Act: -0.0002

Data Index: 1090709 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0406. Min Act: -0.0002

Data Index: 1489445 (Python Code)

Max Activating Token Index: 825

Text #17

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1351330 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0389. Min Act: -0.0002

Data Index: 282406 (C4 (Web Text))

Max Activating Token Index: 409

Text #19

Max Range: 0.0505. Min Range: -0.0505

Max Act: 0.0372. Min Act: -0.0002

Data Index: 433256 (C4 (Web Text))

Max Activating Token Index: 883