Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1104 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.1051. Min Act: -0.0001

Data Index: 302085 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0891. Min Act: -0.0002

Data Index: 920475 (C4 (Web Text))

Max Activating Token Index: 819

Text #2

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0887. Min Act: -0.0002

Data Index: 872317 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0857. Min Act: -0.0002

Data Index: 947983 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0856. Min Act: -0.0001

Data Index: 1173903 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0832. Min Act: -0.0002

Data Index: 831578 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0854. Min Act: -0.0002

Data Index: 583276 (C4 (Web Text))

Max Activating Token Index: 362

Text #7

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0843. Min Act: -0.0002

Data Index: 753265 (C4 (Web Text))

Max Activating Token Index: 309

Text #8

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0845. Min Act: -0.0001

Data Index: 276836 (C4 (Web Text))

Max Activating Token Index: 569

Text #9

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1182618 (C4 (Web Text))

Max Activating Token Index: 499

Text #10

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0809. Min Act: -0.0002

Data Index: 862430 (C4 (Web Text))

Max Activating Token Index: 717

Text #11

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0796. Min Act: -0.0002

Data Index: 299734 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0769. Min Act: -0.0002

Data Index: 356789 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0750. Min Act: -0.0001

Data Index: 1129935 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0764. Min Act: -0.0002

Data Index: 619741 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0777. Min Act: -0.0002

Data Index: 330462 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0755. Min Act: -0.0002

Data Index: 888233 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1320192 (C4 (Web Text))

Max Activating Token Index: 1007

Text #18

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0745. Min Act: -0.0002

Data Index: 1334251 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 0.1051. Min Range: -0.1051

Max Act: 0.0771. Min Act: -0.0001

Data Index: 1041532 (C4 (Web Text))

Max Activating Token Index: 480