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

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

Neuron 3427 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: 1.5927. Min Range: -1.5927

Max Act: 1.5927. Min Act: -0.0001

Data Index: 353775 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.2416. Min Act: -0.0001

Data Index: 984795 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.2175. Min Act: -0.0001

Data Index: 1183659 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.1143. Min Act: -0.0001

Data Index: 410060 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.1786. Min Act: -0.0001

Data Index: 650971 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.0716. Min Act: -0.0001

Data Index: 840552 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.0608. Min Act: -0.0001

Data Index: 664569 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.0440. Min Act: -0.0001

Data Index: 1043272 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.0092. Min Act: -0.0001

Data Index: 354409 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.9750. Min Act: -0.0001

Data Index: 816805 (C4 (Web Text))

Max Activating Token Index: 152

Text #10

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.0038. Min Act: -0.0001

Data Index: 761422 (C4 (Web Text))

Max Activating Token Index: 777

Text #11

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.9732. Min Act: -0.0001

Data Index: 546332 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.9730. Min Act: -0.0001

Data Index: 1124163 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.9922. Min Act: -0.0001

Data Index: 1074891 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.9909. Min Act: -0.0001

Data Index: 398876 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 1.5927. Min Range: -1.5927

Max Act: 1.0164. Min Act: -0.0001

Data Index: 320708 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.9539. Min Act: -0.0001

Data Index: 406798 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.9818. Min Act: -0.0001

Data Index: 581628 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.9859. Min Act: -0.0001

Data Index: 966957 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 1.5927. Min Range: -1.5927

Max Act: 0.9435. Min Act: -0.0001

Data Index: 311028 (C4 (Web Text))

Max Activating Token Index: 40