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

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

Neuron 2663 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.9611. Min Act: -0.0002

Data Index: 485030 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.9351. Min Act: -0.0002

Data Index: 170751 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8884. Min Act: -0.0002

Data Index: 842711 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8724. Min Act: -0.0002

Data Index: 632035 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8412. Min Act: -0.0002

Data Index: 1081856 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8503. Min Act: -0.0002

Data Index: 545999 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8334. Min Act: -0.0002

Data Index: 805424 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8209. Min Act: -0.0002

Data Index: 161419 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8196. Min Act: -0.0002

Data Index: 459332 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8107. Min Act: -0.0002

Data Index: 684979 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8204. Min Act: -0.0002

Data Index: 1251050 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.7910. Min Act: -0.0002

Data Index: 302717 (C4 (Web Text))

Max Activating Token Index: 857

Text #12

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.8093. Min Act: -0.0003

Data Index: 534673 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.7998. Min Act: -0.0002

Data Index: 1292557 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.7886. Min Act: -0.0002

Data Index: 905559 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.7867. Min Act: -0.0002

Data Index: 724400 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.7815. Min Act: -0.0002

Data Index: 923717 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.7662. Min Act: -0.0002

Data Index: 604676 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.7773. Min Act: -0.0002

Data Index: 725763 (C4 (Web Text))

Max Activating Token Index: 26

Text #19

Max Range: 0.9611. Min Range: -0.9611

Max Act: 0.7703. Min Act: -0.0002

Data Index: 188594 (C4 (Web Text))

Max Activating Token Index: 222