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

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

Neuron 2535 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: 0.1054. Min Range: -0.1054

Max Act: 0.1054. Min Act: -0.0002

Data Index: 676282 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0961. Min Act: -0.0002

Data Index: 194970 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0925. Min Act: -0.0002

Data Index: 1178546 (C4 (Web Text))

Max Activating Token Index: 900

Text #3

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0864. Min Act: -0.0002

Data Index: 413491 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0918. Min Act: -0.0002

Data Index: 618272 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0909. Min Act: -0.0002

Data Index: 1222461 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0880. Min Act: -0.0002

Data Index: 1217098 (C4 (Web Text))

Max Activating Token Index: 905

Text #7

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0818. Min Act: -0.0002

Data Index: 795553 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0933. Min Act: -0.0002

Data Index: 542340 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0855. Min Act: -0.0002

Data Index: 811901 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0826. Min Act: -0.0002

Data Index: 697190 (C4 (Web Text))

Max Activating Token Index: 832

Text #11

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0849. Min Act: -0.0002

Data Index: 1195525 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0849. Min Act: -0.0002

Data Index: 659789 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0818. Min Act: -0.0002

Data Index: 546873 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0860. Min Act: -0.0002

Data Index: 815044 (C4 (Web Text))

Max Activating Token Index: 514

Text #15

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0801. Min Act: -0.0002

Data Index: 368478 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0803. Min Act: -0.0002

Data Index: 1198932 (C4 (Web Text))

Max Activating Token Index: 779

Text #17

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0851. Min Act: -0.0002

Data Index: 994040 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0855. Min Act: -0.0002

Data Index: 233710 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0817. Min Act: -0.0002

Data Index: 414494 (C4 (Web Text))

Max Activating Token Index: 230