Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5831 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0997. Min Act: -0.0002

Data Index: 987272 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0905. Min Act: -0.0002

Data Index: 427306 (C4 (Web Text))

Max Activating Token Index: 825

Text #2

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0808. Min Act: -0.0002

Data Index: 627612 (C4 (Web Text))

Max Activating Token Index: 483

Text #3

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0782. Min Act: -0.0002

Data Index: 508661 (C4 (Web Text))

Max Activating Token Index: 938

Text #4

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0745. Min Act: -0.0002

Data Index: 316399 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0732. Min Act: -0.0002

Data Index: 939261 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0740. Min Act: -0.0002

Data Index: 463553 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0706. Min Act: -0.0002

Data Index: 1201397 (C4 (Web Text))

Max Activating Token Index: 114

Text #8

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0726. Min Act: -0.0002

Data Index: 687406 (C4 (Web Text))

Max Activating Token Index: 305

Text #9

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1348515 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0680. Min Act: -0.0002

Data Index: 167163 (C4 (Web Text))

Max Activating Token Index: 597

Text #11

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0699. Min Act: -0.0002

Data Index: 1141940 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0670. Min Act: -0.0002

Data Index: 825463 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0666. Min Act: -0.0002

Data Index: 1270528 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0617. Min Act: -0.0002

Data Index: 376260 (C4 (Web Text))

Max Activating Token Index: 731

Text #15

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0640. Min Act: -0.0002

Data Index: 544600 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0636. Min Act: -0.0002

Data Index: 691942 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0632. Min Act: -0.0002

Data Index: 969442 (C4 (Web Text))

Max Activating Token Index: 351

Text #18

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0610. Min Act: -0.0002

Data Index: 325663 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0629. Min Act: -0.0002

Data Index: 316185 (C4 (Web Text))

Max Activating Token Index: 897