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

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

Neuron 4055 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: 0.1020. Min Range: -0.1020

Max Act: 0.0905. Min Act: -0.0002

Data Index: 751483 (C4 (Web Text))

Max Activating Token Index: 283

Text #1

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0991. Min Act: -0.0002

Data Index: 1075623 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.1020. Min Act: -0.0002

Data Index: 814094 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0817. Min Act: -0.0002

Data Index: 793414 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0705. Min Act: -0.0002

Data Index: 98056 (C4 (Web Text))

Max Activating Token Index: 818

Text #5

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0831. Min Act: -0.0002

Data Index: 700750 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0720. Min Act: -0.0002

Data Index: 1108211 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0699. Min Act: -0.0002

Data Index: 1324253 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0765. Min Act: -0.0002

Data Index: 528034 (C4 (Web Text))

Max Activating Token Index: 418

Text #9

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0759. Min Act: -0.0002

Data Index: 668565 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0759. Min Act: -0.0002

Data Index: 588511 (C4 (Web Text))

Max Activating Token Index: 225

Text #11

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0749. Min Act: -0.0002

Data Index: 661365 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0667. Min Act: -0.0002

Data Index: 1082034 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0713. Min Act: -0.0002

Data Index: 739808 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0705. Min Act: -0.0002

Data Index: 499131 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0751. Min Act: -0.0002

Data Index: 510895 (C4 (Web Text))

Max Activating Token Index: 759

Text #16

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0717. Min Act: -0.0002

Data Index: 909220 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0720. Min Act: -0.0002

Data Index: 813409 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0708. Min Act: -0.0002

Data Index: 435613 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 0.1020. Min Range: -0.1020

Max Act: 0.0729. Min Act: -0.0002

Data Index: 663240 (C4 (Web Text))

Max Activating Token Index: 960