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

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

Neuron 1585 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: 0.1072. Min Range: -0.1072

Max Act: 0.1072. Min Act: -0.0002

Data Index: 485267 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0896. Min Act: -0.0002

Data Index: 358285 (C4 (Web Text))

Max Activating Token Index: 374

Text #2

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0906. Min Act: -0.0002

Data Index: 919214 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0916. Min Act: -0.0002

Data Index: 573071 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0898. Min Act: -0.0002

Data Index: 575649 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0888. Min Act: -0.0002

Data Index: 1038777 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0972. Min Act: -0.0002

Data Index: 295325 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0978. Min Act: -0.0002

Data Index: 614374 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0875. Min Act: -0.0002

Data Index: 818751 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0873. Min Act: -0.0002

Data Index: 110424 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0862. Min Act: -0.0002

Data Index: 47430 (C4 (Web Text))

Max Activating Token Index: 34

Text #11

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0859. Min Act: -0.0002

Data Index: 1309102 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0821. Min Act: -0.0002

Data Index: 47988 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0785. Min Act: -0.0002

Data Index: 1197574 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0809. Min Act: -0.0002

Data Index: 788043 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0842. Min Act: -0.0002

Data Index: 799187 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0827. Min Act: -0.0002

Data Index: 616141 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0832. Min Act: -0.0002

Data Index: 118532 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0747. Min Act: -0.0002

Data Index: 104726 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0748. Min Act: -0.0002

Data Index: 290230 (C4 (Web Text))

Max Activating Token Index: 135