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

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

Neuron 1862 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: 0.0798. Min Range: -0.0798

Max Act: 0.0798. Min Act: -0.0002

Data Index: 800573 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0699. Min Act: -0.0002

Data Index: 715665 (C4 (Web Text))

Max Activating Token Index: 810

Text #2

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0763. Min Act: -0.0002

Data Index: 910165 (C4 (Web Text))

Max Activating Token Index: 21

Text #3

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1214650 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0712. Min Act: -0.0002

Data Index: 854315 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0713. Min Act: -0.0002

Data Index: 1022059 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0633. Min Act: -0.0002

Data Index: 318118 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0606. Min Act: -0.0002

Data Index: 140215 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0612. Min Act: -0.0002

Data Index: 41398 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1073997 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0555. Min Act: -0.0002

Data Index: 286812 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0586. Min Act: -0.0002

Data Index: 892239 (C4 (Web Text))

Max Activating Token Index: 325

Text #12

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0544. Min Act: -0.0002

Data Index: 743700 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0556. Min Act: -0.0002

Data Index: 105576 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0584. Min Act: -0.0002

Data Index: 217554 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1162201 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0591. Min Act: -0.0002

Data Index: 1236989 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0584. Min Act: -0.0002

Data Index: 131900 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0572. Min Act: -0.0002

Data Index: 422941 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0575. Min Act: -0.0002

Data Index: 34870 (C4 (Web Text))

Max Activating Token Index: 759