Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3419 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0560. Min Act: -0.0001

Data Index: 638420 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0513. Min Act: -0.0000

Data Index: 397747 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0515. Min Act: -0.0000

Data Index: 531787 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0437. Min Act: -0.0000

Data Index: 857180 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0419. Min Act: -0.0000

Data Index: 1240893 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0391. Min Act: -0.0001

Data Index: 400674 (C4 (Web Text))

Max Activating Token Index: 768

Text #6

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0381. Min Act: -0.0000

Data Index: 468898 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0397. Min Act: -0.0000

Data Index: 1017865 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0363. Min Act: -0.0001

Data Index: 428219 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0416. Min Act: -0.0001

Data Index: 538025 (C4 (Web Text))

Max Activating Token Index: 725

Text #10

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0367. Min Act: -0.0001

Data Index: 1239719 (C4 (Web Text))

Max Activating Token Index: 385

Text #11

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0347. Min Act: -0.0001

Data Index: 177096 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0360. Min Act: -0.0000

Data Index: 31806 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0330. Min Act: -0.0001

Data Index: 689144 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0321. Min Act: -0.0001

Data Index: 1141523 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0318. Min Act: -0.0000

Data Index: 1049446 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0328. Min Act: -0.0001

Data Index: 1161276 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0310. Min Act: -0.0001

Data Index: 395457 (C4 (Web Text))

Max Activating Token Index: 450

Text #18

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0315. Min Act: -0.0000

Data Index: 536744 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 0.0560. Min Range: -0.0560

Max Act: 0.0317. Min Act: -0.0001

Data Index: 613778 (C4 (Web Text))

Max Activating Token Index: 637