Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3853 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.2053. Min Act: -0.0001

Data Index: 1006648 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.2082. Min Act: -0.0001

Data Index: 1214647 (C4 (Web Text))

Max Activating Token Index: 534

Text #2

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1856. Min Act: -0.0001

Data Index: 968204 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1782. Min Act: -0.0001

Data Index: 1345096 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1718. Min Act: -0.0001

Data Index: 911574 (C4 (Web Text))

Max Activating Token Index: 724

Text #5

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1854. Min Act: -0.0001

Data Index: 577903 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1688. Min Act: -0.0001

Data Index: 302429 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1770. Min Act: -0.0001

Data Index: 916822 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1811. Min Act: -0.0001

Data Index: 39583 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1914. Min Act: -0.0001

Data Index: 1346796 (C4 (Web Text))

Max Activating Token Index: 345

Text #10

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1732. Min Act: -0.0001

Data Index: 959596 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1671. Min Act: -0.0001

Data Index: 194126 (C4 (Web Text))

Max Activating Token Index: 583

Text #12

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1693. Min Act: -0.0001

Data Index: 690072 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1606. Min Act: -0.0001

Data Index: 27119 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1742. Min Act: -0.0001

Data Index: 1264378 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1642. Min Act: -0.0001

Data Index: 143218 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1618. Min Act: -0.0001

Data Index: 48522 (C4 (Web Text))

Max Activating Token Index: 441

Text #17

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1493. Min Act: -0.0001

Data Index: 131089 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1620. Min Act: -0.0001

Data Index: 1259814 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.2082. Min Range: -0.2082

Max Act: 0.1395. Min Act: -0.0001

Data Index: 2923 (C4 (Web Text))

Max Activating Token Index: 689