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

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

Neuron 4475 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.8621. Min Act: -0.0000

Data Index: 660347 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.8679. Min Act: -0.0000

Data Index: 539662 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6847. Min Act: -0.0000

Data Index: 571707 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1178290 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.7811. Min Act: -0.0000

Data Index: 536468 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6740. Min Act: -0.0000

Data Index: 784199 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.7300. Min Act: -0.0000

Data Index: 1344772 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.7408. Min Act: -0.0000

Data Index: 337011 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6828. Min Act: -0.0000

Data Index: 850538 (C4 (Web Text))

Max Activating Token Index: 959

Text #9

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6251. Min Act: -0.0000

Data Index: 1076827 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6883. Min Act: -0.0000

Data Index: 600314 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6809. Min Act: -0.0000

Data Index: 904814 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.7055. Min Act: -0.0000

Data Index: 313880 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6315. Min Act: -0.0000

Data Index: 487195 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6174. Min Act: -0.0000

Data Index: 495102 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6045. Min Act: -0.0000

Data Index: 1065748 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6223. Min Act: -0.0000

Data Index: 160290 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6410. Min Act: -0.0000

Data Index: 1114579 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6611. Min Act: -0.0000

Data Index: 980751 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 0.8679. Min Range: -0.8679

Max Act: 0.6101. Min Act: -0.0000

Data Index: 241250 (C4 (Web Text))

Max Activating Token Index: 556