Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2470 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.9243. Min Range: -4.9243

Max Act: 4.9243. Min Act: -0.0000

Data Index: 14199 (C4 (Web Text))

Max Activating Token Index: 970

Text #1

Max Range: 4.9243. Min Range: -4.9243

Max Act: 3.7853. Min Act: -0.0000

Data Index: 575176 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 4.9243. Min Range: -4.9243

Max Act: 3.8974. Min Act: -0.0000

Data Index: 865781 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 4.9243. Min Range: -4.9243

Max Act: 3.6973. Min Act: -0.0000

Data Index: 487606 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 4.9243. Min Range: -4.9243

Max Act: 3.6357. Min Act: -0.0000

Data Index: 1533418 (Python Code)

Max Activating Token Index: 815

Text #5

Max Range: 4.9243. Min Range: -4.9243

Max Act: 3.2218. Min Act: -0.0000

Data Index: 487387 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 4.9243. Min Range: -4.9243

Max Act: 2.9821. Min Act: -0.0000

Data Index: 312413 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 4.9243. Min Range: -4.9243

Max Act: 2.9335. Min Act: -0.0000

Data Index: 939528 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 4.9243. Min Range: -4.9243

Max Act: 2.7338. Min Act: -0.0000

Data Index: 843795 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 4.9243. Min Range: -4.9243

Max Act: 2.8652. Min Act: -0.0000

Data Index: 765266 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 4.9243. Min Range: -4.9243

Max Act: 2.6739. Min Act: -0.0000

Data Index: 1044837 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 4.9243. Min Range: -4.9243

Max Act: 2.8009. Min Act: -0.0000

Data Index: 801738 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 4.9243. Min Range: -4.9243

Max Act: 2.6741. Min Act: -0.0000

Data Index: 187651 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 4.9243. Min Range: -4.9243

Max Act: 2.7131. Min Act: -0.0000

Data Index: 562555 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 4.9243. Min Range: -4.9243

Max Act: 2.8444. Min Act: -0.0000

Data Index: 459509 (C4 (Web Text))

Max Activating Token Index: 757

Text #15

Max Range: 4.9243. Min Range: -4.9243

Max Act: 2.7222. Min Act: -0.0000

Data Index: 669945 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 4.9243. Min Range: -4.9243

Max Act: 2.7186. Min Act: -0.0000

Data Index: 604797 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 4.9243. Min Range: -4.9243

Max Act: 2.5224. Min Act: -0.0000

Data Index: 165816 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 4.9243. Min Range: -4.9243

Max Act: 2.6566. Min Act: -0.0000

Data Index: 1315695 (C4 (Web Text))

Max Activating Token Index: 516

Text #19

Max Range: 4.9243. Min Range: -4.9243

Max Act: 2.5204. Min Act: -0.0000

Data Index: 639692 (C4 (Web Text))

Max Activating Token Index: 283