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

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

Neuron 1559 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.6816. Min Act: -0.0000

Data Index: 662595 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.6096. Min Act: -0.0000

Data Index: 1250699 (C4 (Web Text))

Max Activating Token Index: 977

Text #2

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.6717. Min Act: -0.0000

Data Index: 283100 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.5431. Min Act: -0.0000

Data Index: 24687 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.5320. Min Act: -0.0000

Data Index: 1211458 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.5488. Min Act: -0.0000

Data Index: 998441 (C4 (Web Text))

Max Activating Token Index: 637

Text #6

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.5318. Min Act: -0.0000

Data Index: 500714 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.5511. Min Act: -0.0000

Data Index: 882610 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.5358. Min Act: -0.0000

Data Index: 113979 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.5102. Min Act: -0.0000

Data Index: 591354 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.4645. Min Act: -0.0000

Data Index: 817957 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.4018. Min Act: -0.0000

Data Index: 962599 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.4573. Min Act: -0.0000

Data Index: 697375 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.4248. Min Act: -0.0000

Data Index: 1109654 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.4574. Min Act: -0.0000

Data Index: 869863 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.4063. Min Act: -0.0000

Data Index: 396763 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.4648. Min Act: -0.0000

Data Index: 600471 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.4225. Min Act: -0.0000

Data Index: 513149 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.4198. Min Act: -0.0000

Data Index: 1151922 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.4128. Min Act: -0.0000

Data Index: 610273 (C4 (Web Text))

Max Activating Token Index: 787