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

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

Neuron 238 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: 0.1711. Min Range: -0.1711

Max Act: 0.1711. Min Act: -0.0002

Data Index: 187890 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1022. Min Act: -0.0002

Data Index: 759215 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.0959. Min Act: -0.0002

Data Index: 803567 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1003. Min Act: -0.0002

Data Index: 475004 (C4 (Web Text))

Max Activating Token Index: 724

Text #4

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1037. Min Act: -0.0002

Data Index: 188653 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.0940. Min Act: -0.0002

Data Index: 218774 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.0941. Min Act: -0.0002

Data Index: 183882 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.0933. Min Act: -0.0002

Data Index: 1200833 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.0954. Min Act: -0.0002

Data Index: 930883 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.1010. Min Act: -0.0002

Data Index: 412803 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.0911. Min Act: -0.0002

Data Index: 717742 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.0785. Min Act: -0.0002

Data Index: 429023 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.0927. Min Act: -0.0002

Data Index: 260602 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.0929. Min Act: -0.0002

Data Index: 834762 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.0853. Min Act: -0.0002

Data Index: 404838 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.0916. Min Act: -0.0002

Data Index: 1020215 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.0828. Min Act: -0.0002

Data Index: 444087 (C4 (Web Text))

Max Activating Token Index: 284

Text #17

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.0739. Min Act: -0.0002

Data Index: 45228 (C4 (Web Text))

Max Activating Token Index: 705

Text #18

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.0853. Min Act: -0.0002

Data Index: 50319 (C4 (Web Text))

Max Activating Token Index: 620

Text #19

Max Range: 0.1711. Min Range: -0.1711

Max Act: 0.0909. Min Act: -0.0002

Data Index: 1334299 (C4 (Web Text))

Max Activating Token Index: 570