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

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

Neuron 3200 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4498. Min Range: -5.4498

Max Act: 5.3283. Min Act: -0.0001

Data Index: 1275703 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 5.4498. Min Range: -5.4498

Max Act: 5.1564. Min Act: -0.0001

Data Index: 662539 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 5.4498. Min Range: -5.4498

Max Act: 5.2390. Min Act: -0.0001

Data Index: 1021845 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 5.4498. Min Range: -5.4498

Max Act: 5.4498. Min Act: -0.0001

Data Index: 695953 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 5.4498. Min Range: -5.4498

Max Act: 5.2685. Min Act: -0.0001

Data Index: 1147129 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 5.4498. Min Range: -5.4498

Max Act: 4.7314. Min Act: -0.0001

Data Index: 884476 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 5.4498. Min Range: -5.4498

Max Act: 4.9816. Min Act: -0.0001

Data Index: 692770 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 5.4498. Min Range: -5.4498

Max Act: 4.0146. Min Act: -0.0001

Data Index: 210806 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 5.4498. Min Range: -5.4498

Max Act: 4.3799. Min Act: -0.0001

Data Index: 1056605 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 5.4498. Min Range: -5.4498

Max Act: 4.5574. Min Act: -0.0001

Data Index: 1196409 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 5.4498. Min Range: -5.4498

Max Act: 4.1625. Min Act: -0.0001

Data Index: 993758 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 5.4498. Min Range: -5.4498

Max Act: 4.2204. Min Act: -0.0001

Data Index: 182759 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 5.4498. Min Range: -5.4498

Max Act: 3.4543. Min Act: -0.0001

Data Index: 162330 (C4 (Web Text))

Max Activating Token Index: 713

Text #13

Max Range: 5.4498. Min Range: -5.4498

Max Act: 3.6878. Min Act: -0.0001

Data Index: 278705 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 5.4498. Min Range: -5.4498

Max Act: 3.9541. Min Act: -0.0001

Data Index: 533950 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 5.4498. Min Range: -5.4498

Max Act: 3.7421. Min Act: -0.0001

Data Index: 983289 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 5.4498. Min Range: -5.4498

Max Act: 4.0719. Min Act: -0.0001

Data Index: 4379 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 5.4498. Min Range: -5.4498

Max Act: 3.6856. Min Act: -0.0001

Data Index: 731554 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 5.4498. Min Range: -5.4498

Max Act: 3.9594. Min Act: -0.0001

Data Index: 1358736 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 5.4498. Min Range: -5.4498

Max Act: 3.4641. Min Act: -0.0001

Data Index: 479724 (C4 (Web Text))

Max Activating Token Index: 881