Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1082 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0783. Min Act: -0.0002

Data Index: 790805 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0678. Min Act: -0.0002

Data Index: 794134 (C4 (Web Text))

Max Activating Token Index: 500

Text #2

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0725. Min Act: -0.0001

Data Index: 881768 (C4 (Web Text))

Max Activating Token Index: 49

Text #3

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0669. Min Act: -0.0002

Data Index: 1055971 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1287217 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0644. Min Act: -0.0001

Data Index: 540180 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0647. Min Act: -0.0001

Data Index: 1046788 (C4 (Web Text))

Max Activating Token Index: 81

Text #7

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0641. Min Act: -0.0001

Data Index: 254369 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0581. Min Act: -0.0001

Data Index: 477717 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0710. Min Act: -0.0001

Data Index: 128821 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0667. Min Act: -0.0001

Data Index: 758786 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0575. Min Act: -0.0001

Data Index: 492189 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0575. Min Act: -0.0002

Data Index: 520652 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0589. Min Act: -0.0001

Data Index: 936966 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0649. Min Act: -0.0001

Data Index: 962283 (C4 (Web Text))

Max Activating Token Index: 544

Text #15

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0538. Min Act: -0.0001

Data Index: 58845 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0582. Min Act: -0.0002

Data Index: 201974 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0603. Min Act: -0.0002

Data Index: 413756 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1052909 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.0783. Min Range: -0.0783

Max Act: 0.0527. Min Act: -0.0001

Data Index: 1326387 (C4 (Web Text))

Max Activating Token Index: 579