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

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

Neuron 3082 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.6572. Min Act: -0.0000

Data Index: 530740 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5611. Min Act: -0.0000

Data Index: 351984 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5604. Min Act: -0.0000

Data Index: 1048741 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5390. Min Act: -0.0000

Data Index: 1319471 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5160. Min Act: -0.0000

Data Index: 1359583 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5271. Min Act: -0.0000

Data Index: 1150881 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4882. Min Act: -0.0000

Data Index: 613809 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4549. Min Act: -0.0000

Data Index: 109657 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.5102. Min Act: -0.0000

Data Index: 360604 (C4 (Web Text))

Max Activating Token Index: 1005

Text #9

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4530. Min Act: -0.0000

Data Index: 35382 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4738. Min Act: -0.0000

Data Index: 717828 (C4 (Web Text))

Max Activating Token Index: 357

Text #11

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4986. Min Act: -0.0000

Data Index: 348221 (C4 (Web Text))

Max Activating Token Index: 221

Text #12

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4254. Min Act: -0.0000

Data Index: 1247929 (C4 (Web Text))

Max Activating Token Index: 171

Text #13

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4566. Min Act: -0.0000

Data Index: 1261757 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.3910. Min Act: -0.0000

Data Index: 1211268 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4190. Min Act: -0.0000

Data Index: 893291 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4158. Min Act: -0.0000

Data Index: 15677 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4848. Min Act: -0.0000

Data Index: 809607 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4148. Min Act: -0.0000

Data Index: 1021496 (C4 (Web Text))

Max Activating Token Index: 818

Text #19

Max Range: 0.6572. Min Range: -0.6572

Max Act: 0.4147. Min Act: -0.0000

Data Index: 867538 (C4 (Web Text))

Max Activating Token Index: 96