Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 547 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0494. Min Act: -0.0003

Data Index: 484283 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0458. Min Act: -0.0003

Data Index: 1180697 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0441. Min Act: -0.0003

Data Index: 1165529 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0435. Min Act: -0.0003

Data Index: 964428 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0416. Min Act: -0.0003

Data Index: 1063403 (C4 (Web Text))

Max Activating Token Index: 836

Text #5

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0416. Min Act: -0.0003

Data Index: 930096 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0417. Min Act: -0.0003

Data Index: 838857 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0420. Min Act: -0.0003

Data Index: 607714 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0362. Min Act: -0.0003

Data Index: 305302 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0369. Min Act: -0.0003

Data Index: 1127688 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0379. Min Act: -0.0003

Data Index: 1290399 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0408. Min Act: -0.0003

Data Index: 640567 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0382. Min Act: -0.0003

Data Index: 24756 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0389. Min Act: -0.0003

Data Index: 1060622 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0380. Min Act: -0.0003

Data Index: 685519 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0362. Min Act: -0.0003

Data Index: 21337 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0366. Min Act: -0.0003

Data Index: 868657 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0373. Min Act: -0.0003

Data Index: 1087344 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0371. Min Act: -0.0003

Data Index: 1139919 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0374. Min Act: -0.0003

Data Index: 954633 (C4 (Web Text))

Max Activating Token Index: 150