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

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

Neuron 2912 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0877. Min Act: -0.0000

Data Index: 988508 (C4 (Web Text))

Max Activating Token Index: 464

Text #1

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0822. Min Act: -0.0000

Data Index: 1024200 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0845. Min Act: -0.0000

Data Index: 300496 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0812. Min Act: -0.0000

Data Index: 123411 (C4 (Web Text))

Max Activating Token Index: 525

Text #4

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0771. Min Act: -0.0000

Data Index: 78532 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0740. Min Act: -0.0000

Data Index: 128253 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0819. Min Act: -0.0000

Data Index: 1295269 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0759. Min Act: -0.0000

Data Index: 82212 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0770. Min Act: -0.0000

Data Index: 815375 (C4 (Web Text))

Max Activating Token Index: 987

Text #9

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0768. Min Act: -0.0000

Data Index: 1211351 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0820. Min Act: -0.0000

Data Index: 1080277 (C4 (Web Text))

Max Activating Token Index: 330

Text #11

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0764. Min Act: -0.0000

Data Index: 1300499 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0758. Min Act: -0.0000

Data Index: 1084120 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0757. Min Act: -0.0000

Data Index: 583204 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0722. Min Act: -0.0000

Data Index: 1349759 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0744. Min Act: 0.0000

Data Index: 1058126 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0720. Min Act: -0.0000

Data Index: 379958 (C4 (Web Text))

Max Activating Token Index: 463

Text #17

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0700. Min Act: -0.0000

Data Index: 596765 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0715. Min Act: -0.0000

Data Index: 807156 (C4 (Web Text))

Max Activating Token Index: 451

Text #19

Max Range: 0.0877. Min Range: -0.0877

Max Act: 0.0730. Min Act: -0.0000

Data Index: 632521 (C4 (Web Text))

Max Activating Token Index: 603