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

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

Neuron 1660 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: 0.0583. Min Range: -0.0583

Max Act: 0.0583. Min Act: -0.0002

Data Index: 853530 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0492. Min Act: -0.0002

Data Index: 401944 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0504. Min Act: -0.0002

Data Index: 690053 (C4 (Web Text))

Max Activating Token Index: 782

Text #3

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0438. Min Act: -0.0002

Data Index: 1129564 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0501. Min Act: -0.0002

Data Index: 888724 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0408. Min Act: -0.0002

Data Index: 859129 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0438. Min Act: -0.0002

Data Index: 133543 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0429. Min Act: -0.0002

Data Index: 262936 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0416. Min Act: -0.0002

Data Index: 259809 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0443. Min Act: -0.0002

Data Index: 1131466 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0411. Min Act: -0.0002

Data Index: 656381 (C4 (Web Text))

Max Activating Token Index: 1006

Text #11

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0465. Min Act: -0.0002

Data Index: 332538 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0376. Min Act: -0.0002

Data Index: 284452 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0454. Min Act: -0.0002

Data Index: 990138 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0393. Min Act: -0.0002

Data Index: 441502 (C4 (Web Text))

Max Activating Token Index: 166

Text #15

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0453. Min Act: -0.0002

Data Index: 380611 (C4 (Web Text))

Max Activating Token Index: 271

Text #16

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0387. Min Act: -0.0002

Data Index: 434988 (C4 (Web Text))

Max Activating Token Index: 579

Text #17

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1069182 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0395. Min Act: -0.0002

Data Index: 670932 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0367. Min Act: -0.0002

Data Index: 496799 (C4 (Web Text))

Max Activating Token Index: 113