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

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

Neuron 4812 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: 0.7130. Min Range: -0.7130

Max Act: 0.7130. Min Act: -0.0002

Data Index: 1009594 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6936. Min Act: -0.0002

Data Index: 632916 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6870. Min Act: -0.0002

Data Index: 132837 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6859. Min Act: -0.0002

Data Index: 1080032 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6769. Min Act: -0.0002

Data Index: 993686 (C4 (Web Text))

Max Activating Token Index: 896

Text #5

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6742. Min Act: -0.0002

Data Index: 726953 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6771. Min Act: -0.0002

Data Index: 1064457 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6807. Min Act: -0.0002

Data Index: 807329 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6677. Min Act: -0.0002

Data Index: 1328893 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6710. Min Act: -0.0002

Data Index: 754259 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6713. Min Act: -0.0002

Data Index: 776789 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6656. Min Act: -0.0002

Data Index: 1330818 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6670. Min Act: -0.0002

Data Index: 97777 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6483. Min Act: -0.0002

Data Index: 1008946 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6469. Min Act: -0.0002

Data Index: 1240234 (C4 (Web Text))

Max Activating Token Index: 973

Text #15

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6508. Min Act: -0.0002

Data Index: 763193 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6563. Min Act: -0.0002

Data Index: 1000349 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6251. Min Act: -0.0002

Data Index: 604938 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6172. Min Act: -0.0002

Data Index: 1203654 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 0.7130. Min Range: -0.7130

Max Act: 0.6338. Min Act: -0.0002

Data Index: 627365 (C4 (Web Text))

Max Activating Token Index: 979