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

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

Neuron 3399 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0826. Min Range: -1.0826

Max Act: 1.0524. Min Act: -0.0000

Data Index: 1261464 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 1.0826. Min Range: -1.0826

Max Act: 1.0826. Min Act: -0.0000

Data Index: 979820 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 1.0826. Min Range: -1.0826

Max Act: 1.0374. Min Act: -0.0000

Data Index: 570040 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.9611. Min Act: -0.0000

Data Index: 1109440 (C4 (Web Text))

Max Activating Token Index: 353

Text #4

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.9770. Min Act: -0.0001

Data Index: 743262 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.9401. Min Act: -0.0000

Data Index: 1120626 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.9384. Min Act: -0.0000

Data Index: 206679 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.9092. Min Act: -0.0000

Data Index: 142185 (C4 (Web Text))

Max Activating Token Index: 70

Text #8

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.9270. Min Act: -0.0000

Data Index: 1214099 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 1.0826. Min Range: -1.0826

Max Act: 1.0609. Min Act: -0.0000

Data Index: 14374 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.9402. Min Act: -0.0000

Data Index: 837356 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.9241. Min Act: -0.0000

Data Index: 1348840 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.8911. Min Act: -0.0001

Data Index: 617124 (C4 (Web Text))

Max Activating Token Index: 528

Text #13

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.8391. Min Act: -0.0000

Data Index: 791659 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.9329. Min Act: -0.0000

Data Index: 96951 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.8486. Min Act: -0.0000

Data Index: 831819 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.8791. Min Act: -0.0000

Data Index: 293670 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.8269. Min Act: -0.0000

Data Index: 1073957 (C4 (Web Text))

Max Activating Token Index: 208

Text #18

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.8742. Min Act: -0.0000

Data Index: 468746 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 1.0826. Min Range: -1.0826

Max Act: 0.8665. Min Act: -0.0000

Data Index: 880805 (C4 (Web Text))

Max Activating Token Index: 430