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

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

Neuron 2544 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: 0.0763. Min Range: -0.0763

Max Act: 0.0733. Min Act: -0.0003

Data Index: 637219 (C4 (Web Text))

Max Activating Token Index: 586

Text #1

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0763. Min Act: -0.0003

Data Index: 555987 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0718. Min Act: -0.0003

Data Index: 561853 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0715. Min Act: -0.0003

Data Index: 696835 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0720. Min Act: -0.0002

Data Index: 1173692 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0645. Min Act: -0.0003

Data Index: 40541 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0649. Min Act: -0.0003

Data Index: 211603 (C4 (Web Text))

Max Activating Token Index: 113

Text #7

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0672. Min Act: -0.0003

Data Index: 1216295 (C4 (Web Text))

Max Activating Token Index: 147

Text #8

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0639. Min Act: -0.0003

Data Index: 1278915 (C4 (Web Text))

Max Activating Token Index: 428

Text #9

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0635. Min Act: -0.0003

Data Index: 1097211 (C4 (Web Text))

Max Activating Token Index: 646

Text #10

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0614. Min Act: -0.0003

Data Index: 775931 (C4 (Web Text))

Max Activating Token Index: 709

Text #11

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0609. Min Act: -0.0003

Data Index: 1162738 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0619. Min Act: -0.0003

Data Index: 475763 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0613. Min Act: -0.0003

Data Index: 1324739 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0596. Min Act: -0.0003

Data Index: 1143965 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0615. Min Act: -0.0003

Data Index: 549443 (C4 (Web Text))

Max Activating Token Index: 828

Text #16

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0590. Min Act: -0.0003

Data Index: 1094413 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0602. Min Act: -0.0003

Data Index: 1115995 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0585. Min Act: -0.0003

Data Index: 674819 (C4 (Web Text))

Max Activating Token Index: 421

Text #19

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0597. Min Act: -0.0003

Data Index: 720575 (C4 (Web Text))

Max Activating Token Index: 517