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

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

Neuron 2606 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0735. Min Act: -0.0003

Data Index: 288227 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0697. Min Act: -0.0003

Data Index: 469364 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0710. Min Act: -0.0002

Data Index: 142020 (C4 (Web Text))

Max Activating Token Index: 1001

Text #3

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0708. Min Act: -0.0003

Data Index: 1333662 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0693. Min Act: -0.0003

Data Index: 755022 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0706. Min Act: -0.0002

Data Index: 229449 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0669. Min Act: -0.0002

Data Index: 131973 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0695. Min Act: -0.0003

Data Index: 547199 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0619. Min Act: -0.0003

Data Index: 890658 (C4 (Web Text))

Max Activating Token Index: 170

Text #9

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0657. Min Act: -0.0002

Data Index: 320721 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0639. Min Act: -0.0003

Data Index: 626891 (C4 (Web Text))

Max Activating Token Index: 199

Text #11

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0645. Min Act: -0.0003

Data Index: 317563 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0672. Min Act: -0.0002

Data Index: 589438 (C4 (Web Text))

Max Activating Token Index: 643

Text #13

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0643. Min Act: -0.0003

Data Index: 1091736 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0633. Min Act: -0.0002

Data Index: 554606 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0653. Min Act: -0.0003

Data Index: 16105 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0606. Min Act: -0.0003

Data Index: 803337 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0595. Min Act: -0.0002

Data Index: 147543 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0596. Min Act: -0.0003

Data Index: 941261 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.0735. Min Range: -0.0735

Max Act: 0.0606. Min Act: -0.0003

Data Index: 853893 (C4 (Web Text))

Max Activating Token Index: 864