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

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

Neuron 4967 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0955. Min Act: -0.0002

Data Index: 1197239 (C4 (Web Text))

Max Activating Token Index: 596

Text #1

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0922. Min Act: -0.0002

Data Index: 638950 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0923. Min Act: -0.0002

Data Index: 1243660 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0878. Min Act: -0.0002

Data Index: 473071 (C4 (Web Text))

Max Activating Token Index: 692

Text #4

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0912. Min Act: -0.0002

Data Index: 757552 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.1080. Min Act: -0.0002

Data Index: 460214 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0902. Min Act: -0.0002

Data Index: 1195094 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0899. Min Act: -0.0002

Data Index: 380298 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0921. Min Act: -0.0002

Data Index: 192588 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0801. Min Act: -0.0002

Data Index: 819353 (C4 (Web Text))

Max Activating Token Index: 84

Text #10

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0913. Min Act: -0.0002

Data Index: 916208 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0853. Min Act: -0.0002

Data Index: 439510 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0782. Min Act: -0.0002

Data Index: 1274414 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0781. Min Act: -0.0002

Data Index: 685454 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0753. Min Act: -0.0002

Data Index: 304891 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0873. Min Act: -0.0002

Data Index: 1084741 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0726. Min Act: -0.0002

Data Index: 1046328 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0823. Min Act: -0.0002

Data Index: 1112881 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0846. Min Act: -0.0002

Data Index: 19309 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.1080. Min Range: -0.1080

Max Act: 0.0775. Min Act: -0.0002

Data Index: 80416 (C4 (Web Text))

Max Activating Token Index: 26