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

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

Neuron 1647 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: 0.1061. Min Range: -0.1061

Max Act: 0.1061. Min Act: -0.0002

Data Index: 808200 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0955. Min Act: -0.0002

Data Index: 398325 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0890. Min Act: -0.0002

Data Index: 54881 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0907. Min Act: -0.0002

Data Index: 871930 (C4 (Web Text))

Max Activating Token Index: 242

Text #4

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0879. Min Act: -0.0002

Data Index: 629685 (C4 (Web Text))

Max Activating Token Index: 449

Text #5

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0810. Min Act: -0.0002

Data Index: 357830 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0774. Min Act: -0.0002

Data Index: 739170 (C4 (Web Text))

Max Activating Token Index: 199

Text #7

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0790. Min Act: -0.0002

Data Index: 992357 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0738. Min Act: -0.0002

Data Index: 492473 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0741. Min Act: -0.0002

Data Index: 557277 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0704. Min Act: -0.0002

Data Index: 131397 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0752. Min Act: -0.0002

Data Index: 807947 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0747. Min Act: -0.0002

Data Index: 127054 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0694. Min Act: -0.0002

Data Index: 380978 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0772. Min Act: -0.0002

Data Index: 950411 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0682. Min Act: -0.0002

Data Index: 57628 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0652. Min Act: -0.0002

Data Index: 938513 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0667. Min Act: -0.0002

Data Index: 846997 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0587. Min Act: -0.0002

Data Index: 936247 (C4 (Web Text))

Max Activating Token Index: 251

Text #19

Max Range: 0.1061. Min Range: -0.1061

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1120701 (C4 (Web Text))

Max Activating Token Index: 447