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

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

Neuron 1534 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0426. Min Act: -0.0005

Data Index: 316748 (C4 (Web Text))

Max Activating Token Index: 849

Text #1

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0440. Min Act: -0.0005

Data Index: 960469 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0410. Min Act: -0.0005

Data Index: 37544 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0396. Min Act: -0.0005

Data Index: 712071 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0384. Min Act: -0.0005

Data Index: 1229268 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0381. Min Act: -0.0005

Data Index: 1142599 (C4 (Web Text))

Max Activating Token Index: 234

Text #6

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0385. Min Act: -0.0005

Data Index: 1122041 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0379. Min Act: -0.0005

Data Index: 1172520 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0388. Min Act: -0.0005

Data Index: 658874 (C4 (Web Text))

Max Activating Token Index: 534

Text #9

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0363. Min Act: -0.0005

Data Index: 180609 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0382. Min Act: -0.0005

Data Index: 1051413 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0374. Min Act: -0.0005

Data Index: 364190 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0380. Min Act: -0.0005

Data Index: 1090769 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0361. Min Act: -0.0005

Data Index: 548537 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0380. Min Act: -0.0005

Data Index: 951799 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0370. Min Act: -0.0005

Data Index: 926010 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0367. Min Act: -0.0005

Data Index: 17152 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0375. Min Act: -0.0005

Data Index: 956679 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0353. Min Act: -0.0005

Data Index: 737385 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0367. Min Act: -0.0005

Data Index: 169484 (C4 (Web Text))

Max Activating Token Index: 210