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

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

Neuron 2049 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0001

Data Index: 267393 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0729. Min Act: -0.0002

Data Index: 85536 (C4 (Web Text))

Max Activating Token Index: 249

Text #2

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0782. Min Act: -0.0002

Data Index: 218562 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0723. Min Act: -0.0002

Data Index: 477662 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0750. Min Act: -0.0002

Data Index: 460251 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0653. Min Act: -0.0002

Data Index: 734048 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0697. Min Act: -0.0002

Data Index: 1267021 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0670. Min Act: -0.0002

Data Index: 246893 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0746. Min Act: -0.0002

Data Index: 281344 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0714. Min Act: -0.0001

Data Index: 962864 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0709. Min Act: -0.0001

Data Index: 1156382 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0728. Min Act: -0.0002

Data Index: 92691 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0704. Min Act: -0.0002

Data Index: 533683 (C4 (Web Text))

Max Activating Token Index: 636

Text #13

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0680. Min Act: -0.0001

Data Index: 1092191 (C4 (Web Text))

Max Activating Token Index: 162

Text #14

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0719. Min Act: -0.0001

Data Index: 1470973 (Python Code)

Max Activating Token Index: 514

Text #15

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0648. Min Act: -0.0001

Data Index: 1316188 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0666. Min Act: -0.0001

Data Index: 201941 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0605. Min Act: -0.0002

Data Index: 329212 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0689. Min Act: -0.0002

Data Index: 391599 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0640. Min Act: -0.0001

Data Index: 1084845 (C4 (Web Text))

Max Activating Token Index: 89