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

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

Neuron 4544 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.6807. Min Act: -0.0002

Data Index: 524083 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5314. Min Act: -0.0002

Data Index: 70611 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.6067. Min Act: -0.0002

Data Index: 386994 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5618. Min Act: -0.0002

Data Index: 1348065 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5667. Min Act: -0.0002

Data Index: 694650 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5366. Min Act: -0.0002

Data Index: 1296535 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5490. Min Act: -0.0002

Data Index: 988273 (C4 (Web Text))

Max Activating Token Index: 947

Text #7

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5206. Min Act: -0.0002

Data Index: 633589 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5730. Min Act: -0.0002

Data Index: 426136 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5206. Min Act: -0.0002

Data Index: 462186 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5357. Min Act: -0.0002

Data Index: 895837 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5349. Min Act: -0.0002

Data Index: 57826 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5660. Min Act: -0.0002

Data Index: 1073825 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5246. Min Act: -0.0002

Data Index: 1258443 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4957. Min Act: -0.0002

Data Index: 27403 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5463. Min Act: -0.0002

Data Index: 1064982 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5376. Min Act: -0.0002

Data Index: 955122 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5377. Min Act: -0.0002

Data Index: 36695 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.5229. Min Act: -0.0002

Data Index: 627281 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.6807. Min Range: -0.6807

Max Act: 0.4889. Min Act: -0.0002

Data Index: 625135 (C4 (Web Text))

Max Activating Token Index: 826