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

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

Neuron 3450 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: 0.0753. Min Range: -0.0753

Max Act: 0.0753. Min Act: -0.0002

Data Index: 76086 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0687. Min Act: -0.0002

Data Index: 402762 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0653. Min Act: -0.0002

Data Index: 921000 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0614. Min Act: -0.0002

Data Index: 854384 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0618. Min Act: -0.0002

Data Index: 694378 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0617. Min Act: -0.0002

Data Index: 196214 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0642. Min Act: -0.0002

Data Index: 62904 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0573. Min Act: -0.0002

Data Index: 543900 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0573. Min Act: -0.0002

Data Index: 453909 (C4 (Web Text))

Max Activating Token Index: 603

Text #9

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0569. Min Act: -0.0002

Data Index: 885977 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0589. Min Act: -0.0002

Data Index: 782166 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1137395 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1032807 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0544. Min Act: -0.0002

Data Index: 60050 (C4 (Web Text))

Max Activating Token Index: 247

Text #14

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0526. Min Act: -0.0002

Data Index: 351166 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0546. Min Act: -0.0002

Data Index: 497053 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0523. Min Act: -0.0002

Data Index: 200462 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0594. Min Act: -0.0002

Data Index: 975697 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0526. Min Act: -0.0002

Data Index: 817787 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.0753. Min Range: -0.0753

Max Act: 0.0522. Min Act: -0.0002

Data Index: 537810 (C4 (Web Text))

Max Activating Token Index: 79