Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3138 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1057902 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0482. Min Act: -0.0002

Data Index: 1391169 (Python Code)

Max Activating Token Index: 72

Text #2

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0425. Min Act: -0.0002

Data Index: 444170 (C4 (Web Text))

Max Activating Token Index: 218

Text #3

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1473112 (Python Code)

Max Activating Token Index: 833

Text #4

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0384. Min Act: -0.0002

Data Index: 167895 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0377. Min Act: -0.0002

Data Index: 1211290 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0323. Min Act: -0.0002

Data Index: 1543858 (Python Code)

Max Activating Token Index: 94

Text #7

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1280942 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0334. Min Act: -0.0002

Data Index: 480697 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0271. Min Act: -0.0002

Data Index: 207140 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1218047 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0321. Min Act: -0.0002

Data Index: 528711 (C4 (Web Text))

Max Activating Token Index: 506

Text #12

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0314. Min Act: -0.0002

Data Index: 1263557 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0346. Min Act: -0.0002

Data Index: 103075 (C4 (Web Text))

Max Activating Token Index: 678

Text #14

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0389. Min Act: -0.0002

Data Index: 1574501 (Python Code)

Max Activating Token Index: 191

Text #15

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0339. Min Act: -0.0002

Data Index: 808671 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0315. Min Act: -0.0002

Data Index: 7163 (C4 (Web Text))

Max Activating Token Index: 1011

Text #17

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0295. Min Act: -0.0003

Data Index: 868128 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1642650 (Python Code)

Max Activating Token Index: 882

Text #19

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0211. Min Act: -0.0002

Data Index: 792822 (C4 (Web Text))

Max Activating Token Index: 767