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

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

Neuron 961 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: 0.0570. Min Range: -0.0570

Max Act: 0.0570. Min Act: -0.0006

Data Index: 95566 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0519. Min Act: -0.0006

Data Index: 138204 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0484. Min Act: -0.0006

Data Index: 996366 (C4 (Web Text))

Max Activating Token Index: 928

Text #3

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0467. Min Act: -0.0006

Data Index: 356063 (C4 (Web Text))

Max Activating Token Index: 527

Text #4

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0450. Min Act: -0.0006

Data Index: 447768 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0431. Min Act: -0.0006

Data Index: 1264827 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0417. Min Act: -0.0006

Data Index: 729706 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0428. Min Act: -0.0006

Data Index: 779736 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0408. Min Act: -0.0006

Data Index: 415318 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0387. Min Act: -0.0006

Data Index: 1214552 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0396. Min Act: -0.0006

Data Index: 329186 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0402. Min Act: -0.0006

Data Index: 1182397 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0388. Min Act: -0.0005

Data Index: 390754 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0412. Min Act: -0.0006

Data Index: 439684 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0393. Min Act: -0.0006

Data Index: 1272520 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0418. Min Act: -0.0006

Data Index: 177827 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0383. Min Act: -0.0006

Data Index: 50636 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0358. Min Act: -0.0006

Data Index: 155945 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0378. Min Act: -0.0006

Data Index: 611697 (C4 (Web Text))

Max Activating Token Index: 168

Text #19

Max Range: 0.0570. Min Range: -0.0570

Max Act: 0.0376. Min Act: -0.0006

Data Index: 1130016 (C4 (Web Text))

Max Activating Token Index: 395