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

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

Neuron 512 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0399. Min Act: -0.0005

Data Index: 149042 (C4 (Web Text))

Max Activating Token Index: 820

Text #1

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0407. Min Act: -0.0006

Data Index: 658472 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0373. Min Act: -0.0005

Data Index: 1243686 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0395. Min Act: -0.0006

Data Index: 305360 (C4 (Web Text))

Max Activating Token Index: 995

Text #4

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0381. Min Act: -0.0006

Data Index: 144550 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0366. Min Act: -0.0005

Data Index: 38465 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0366. Min Act: -0.0005

Data Index: 1335449 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0369. Min Act: -0.0005

Data Index: 949479 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0352. Min Act: -0.0005

Data Index: 1320444 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0374. Min Act: -0.0005

Data Index: 319693 (C4 (Web Text))

Max Activating Token Index: 806

Text #10

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0346. Min Act: -0.0005

Data Index: 315238 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0372. Min Act: -0.0005

Data Index: 638519 (C4 (Web Text))

Max Activating Token Index: 882

Text #12

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0371. Min Act: -0.0006

Data Index: 768670 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0372. Min Act: -0.0005

Data Index: 1341335 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0356. Min Act: -0.0006

Data Index: 1307438 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0362. Min Act: -0.0006

Data Index: 725955 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0362. Min Act: -0.0006

Data Index: 753498 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0369. Min Act: -0.0005

Data Index: 1256470 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0346. Min Act: -0.0005

Data Index: 484421 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0360. Min Act: -0.0005

Data Index: 509253 (C4 (Web Text))

Max Activating Token Index: 748