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

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

Neuron 1659 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0893. Min Act: -0.0001

Data Index: 426283 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0863. Min Act: -0.0001

Data Index: 1319483 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0892. Min Act: -0.0001

Data Index: 552424 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0898. Min Act: -0.0001

Data Index: 452033 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0864. Min Act: -0.0001

Data Index: 740985 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0863. Min Act: -0.0001

Data Index: 323846 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0827. Min Act: -0.0001

Data Index: 1087790 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0825. Min Act: -0.0001

Data Index: 1225406 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0842. Min Act: -0.0001

Data Index: 683128 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1074599 (C4 (Web Text))

Max Activating Token Index: 482

Text #10

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0798. Min Act: -0.0001

Data Index: 423690 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0825. Min Act: -0.0001

Data Index: 452728 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0838. Min Act: -0.0001

Data Index: 679110 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0819. Min Act: -0.0001

Data Index: 437783 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0811. Min Act: -0.0001

Data Index: 715294 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0825. Min Act: -0.0001

Data Index: 1251503 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0790. Min Act: -0.0001

Data Index: 237946 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0781. Min Act: -0.0001

Data Index: 962347 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0749. Min Act: -0.0001

Data Index: 105784 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0777. Min Act: -0.0001

Data Index: 316543 (C4 (Web Text))

Max Activating Token Index: 644