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

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

Neuron 685 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: 0.6746. Min Range: -0.6746

Max Act: 0.6746. Min Act: -0.0000

Data Index: 1500447 (Python Code)

Max Activating Token Index: 717

Text #1

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.6262. Min Act: -0.0000

Data Index: 1321777 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.6264. Min Act: -0.0000

Data Index: 958465 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.5962. Min Act: -0.0000

Data Index: 1615450 (Python Code)

Max Activating Token Index: 614

Text #4

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.5770. Min Act: -0.0000

Data Index: 1559020 (Python Code)

Max Activating Token Index: 252

Text #5

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.6027. Min Act: -0.0000

Data Index: 747623 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.5839. Min Act: -0.0000

Data Index: 1577673 (Python Code)

Max Activating Token Index: 370

Text #7

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.6108. Min Act: -0.0000

Data Index: 758821 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.5529. Min Act: -0.0000

Data Index: 1513905 (Python Code)

Max Activating Token Index: 751

Text #9

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.5838. Min Act: -0.0000

Data Index: 1084148 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.5607. Min Act: -0.0000

Data Index: 1075636 (C4 (Web Text))

Max Activating Token Index: 982

Text #11

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.5608. Min Act: -0.0000

Data Index: 283424 (C4 (Web Text))

Max Activating Token Index: 1007

Text #12

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.5708. Min Act: -0.0000

Data Index: 244087 (C4 (Web Text))

Max Activating Token Index: 208

Text #13

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.5493. Min Act: -0.0000

Data Index: 1468203 (Python Code)

Max Activating Token Index: 482

Text #14

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.5515. Min Act: -0.0000

Data Index: 1437214 (Python Code)

Max Activating Token Index: 130

Text #15

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.5129. Min Act: -0.0000

Data Index: 831152 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.5551. Min Act: -0.0000

Data Index: 1647451 (Python Code)

Max Activating Token Index: 843

Text #17

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1405062 (Python Code)

Max Activating Token Index: 912

Text #18

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.5380. Min Act: -0.0000

Data Index: 1575760 (Python Code)

Max Activating Token Index: 790

Text #19

Max Range: 0.6746. Min Range: -0.6746

Max Act: 0.5421. Min Act: -0.0000

Data Index: 1614543 (Python Code)

Max Activating Token Index: 257