Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3348 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.9629. Min Act: -0.0001

Data Index: 706469 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.8827. Min Act: -0.0001

Data Index: 14649 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.8683. Min Act: -0.0001

Data Index: 170144 (C4 (Web Text))

Max Activating Token Index: 64

Text #3

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.8434. Min Act: -0.0001

Data Index: 59689 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.7871. Min Act: -0.0001

Data Index: 567236 (C4 (Web Text))

Max Activating Token Index: 157

Text #5

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.8557. Min Act: -0.0001

Data Index: 433810 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.7894. Min Act: -0.0001

Data Index: 908378 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.8122. Min Act: -0.0001

Data Index: 141221 (C4 (Web Text))

Max Activating Token Index: 899

Text #8

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.7917. Min Act: -0.0001

Data Index: 25508 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.7909. Min Act: -0.0001

Data Index: 969599 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.7951. Min Act: -0.0001

Data Index: 1128805 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.7128. Min Act: -0.0001

Data Index: 1304548 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.7342. Min Act: -0.0001

Data Index: 1047498 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.7102. Min Act: -0.0001

Data Index: 400403 (C4 (Web Text))

Max Activating Token Index: 403

Text #14

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.6843. Min Act: -0.0001

Data Index: 1285529 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.7269. Min Act: -0.0001

Data Index: 739178 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.7634. Min Act: -0.0001

Data Index: 880204 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.6839. Min Act: -0.0001

Data Index: 1221325 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.7184. Min Act: -0.0001

Data Index: 305055 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 0.9629. Min Range: -0.9629

Max Act: 0.6586. Min Act: -0.0000

Data Index: 573996 (C4 (Web Text))

Max Activating Token Index: 883