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

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

Neuron 3700 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: 0.1305. Min Range: -0.1305

Max Act: 0.1305. Min Act: -0.0002

Data Index: 1112910 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1242368 (C4 (Web Text))

Max Activating Token Index: 734

Text #2

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1197. Min Act: -0.0002

Data Index: 404848 (C4 (Web Text))

Max Activating Token Index: 83

Text #3

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1035. Min Act: -0.0001

Data Index: 893727 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.1032. Min Act: -0.0002

Data Index: 282350 (C4 (Web Text))

Max Activating Token Index: 6

Text #5

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0976. Min Act: -0.0002

Data Index: 261745 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0938. Min Act: -0.0002

Data Index: 441697 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0950. Min Act: -0.0002

Data Index: 375593 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0909. Min Act: -0.0002

Data Index: 148839 (C4 (Web Text))

Max Activating Token Index: 859

Text #9

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0903. Min Act: -0.0002

Data Index: 317583 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0856. Min Act: -0.0001

Data Index: 178591 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0842. Min Act: -0.0001

Data Index: 656418 (C4 (Web Text))

Max Activating Token Index: 939

Text #12

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0889. Min Act: -0.0002

Data Index: 388296 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0974. Min Act: -0.0002

Data Index: 497603 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0902. Min Act: -0.0002

Data Index: 7510 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0865. Min Act: -0.0001

Data Index: 271084 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0866. Min Act: -0.0002

Data Index: 134638 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0828. Min Act: -0.0002

Data Index: 1140036 (C4 (Web Text))

Max Activating Token Index: 872

Text #18

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0889. Min Act: -0.0002

Data Index: 556945 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.1305. Min Range: -0.1305

Max Act: 0.0912. Min Act: -0.0002

Data Index: 1125821 (C4 (Web Text))

Max Activating Token Index: 397