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

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

Neuron 589 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: 0.0467. Min Range: -0.0467

Max Act: 0.0467. Min Act: -0.0003

Data Index: 150598 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0407. Min Act: -0.0003

Data Index: 367592 (C4 (Web Text))

Max Activating Token Index: 689

Text #2

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0392. Min Act: -0.0003

Data Index: 1087985 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0394. Min Act: -0.0003

Data Index: 48424 (C4 (Web Text))

Max Activating Token Index: 864

Text #4

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0386. Min Act: -0.0003

Data Index: 507421 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0391. Min Act: -0.0003

Data Index: 522151 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0370. Min Act: -0.0003

Data Index: 658848 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0385. Min Act: -0.0003

Data Index: 409413 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0400. Min Act: -0.0003

Data Index: 12663 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0394. Min Act: -0.0003

Data Index: 233763 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0387. Min Act: -0.0002

Data Index: 223462 (C4 (Web Text))

Max Activating Token Index: 89

Text #11

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0385. Min Act: -0.0003

Data Index: 1218135 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0377. Min Act: -0.0003

Data Index: 809445 (C4 (Web Text))

Max Activating Token Index: 605

Text #13

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0379. Min Act: -0.0003

Data Index: 1065846 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0378. Min Act: -0.0003

Data Index: 681684 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0377. Min Act: -0.0003

Data Index: 94606 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0389. Min Act: -0.0003

Data Index: 380674 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0377. Min Act: -0.0003

Data Index: 698009 (C4 (Web Text))

Max Activating Token Index: 88

Text #18

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0377. Min Act: -0.0003

Data Index: 872269 (C4 (Web Text))

Max Activating Token Index: 325

Text #19

Max Range: 0.0467. Min Range: -0.0467

Max Act: 0.0369. Min Act: -0.0003

Data Index: 226732 (C4 (Web Text))

Max Activating Token Index: 792