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

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

Neuron 475 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: 0.0810. Min Range: -0.0810

Max Act: 0.0810. Min Act: -0.0002

Data Index: 92921 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1115057 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1273608 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0763. Min Act: -0.0002

Data Index: 861692 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0710. Min Act: -0.0002

Data Index: 152311 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0720. Min Act: -0.0002

Data Index: 974160 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0704. Min Act: -0.0001

Data Index: 489540 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0696. Min Act: -0.0002

Data Index: 1308672 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0687. Min Act: -0.0002

Data Index: 45178 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0688. Min Act: -0.0002

Data Index: 557563 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1285021 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1350912 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0634. Min Act: -0.0002

Data Index: 581187 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0644. Min Act: -0.0002

Data Index: 177017 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1279818 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0629. Min Act: -0.0002

Data Index: 334604 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0616. Min Act: -0.0002

Data Index: 744428 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0595. Min Act: -0.0002

Data Index: 300407 (C4 (Web Text))

Max Activating Token Index: 906

Text #18

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0616. Min Act: -0.0002

Data Index: 938451 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.0810. Min Range: -0.0810

Max Act: 0.0602. Min Act: -0.0002

Data Index: 468077 (C4 (Web Text))

Max Activating Token Index: 19