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

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

Neuron 100 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: 0.1054. Min Range: -0.1054

Max Act: 0.1054. Min Act: -0.0002

Data Index: 837694 (C4 (Web Text))

Max Activating Token Index: 225

Text #1

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.1033. Min Act: -0.0002

Data Index: 649492 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.1027. Min Act: -0.0002

Data Index: 527500 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.1045. Min Act: -0.0002

Data Index: 1352670 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.1003. Min Act: -0.0002

Data Index: 1112057 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0968. Min Act: -0.0002

Data Index: 1088697 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.1005. Min Act: -0.0002

Data Index: 1262245 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0964. Min Act: -0.0002

Data Index: 1047440 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0931. Min Act: -0.0002

Data Index: 943317 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0944. Min Act: -0.0002

Data Index: 315774 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0940. Min Act: -0.0002

Data Index: 682438 (C4 (Web Text))

Max Activating Token Index: 208

Text #11

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0884. Min Act: -0.0002

Data Index: 51152 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0891. Min Act: -0.0002

Data Index: 870424 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0905. Min Act: -0.0002

Data Index: 464377 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0865. Min Act: -0.0002

Data Index: 438559 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0858. Min Act: -0.0002

Data Index: 71714 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0847. Min Act: -0.0002

Data Index: 730303 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0923. Min Act: -0.0002

Data Index: 632303 (C4 (Web Text))

Max Activating Token Index: 608

Text #18

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0869. Min Act: -0.0002

Data Index: 721160 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 0.1054. Min Range: -0.1054

Max Act: 0.0873. Min Act: -0.0002

Data Index: 1217693 (C4 (Web Text))

Max Activating Token Index: 650