Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2024 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0737. Min Act: -0.0002

Data Index: 769617 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0644. Min Act: -0.0001

Data Index: 76797 (C4 (Web Text))

Max Activating Token Index: 511

Text #2

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0627. Min Act: -0.0001

Data Index: 951620 (C4 (Web Text))

Max Activating Token Index: 280

Text #3

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0647. Min Act: -0.0001

Data Index: 676108 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0638. Min Act: -0.0001

Data Index: 708875 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0626. Min Act: -0.0001

Data Index: 1137519 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1292621 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1220320 (C4 (Web Text))

Max Activating Token Index: 150

Text #8

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0581. Min Act: -0.0002

Data Index: 1225565 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0573. Min Act: -0.0001

Data Index: 1114827 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0572. Min Act: -0.0002

Data Index: 37509 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0569. Min Act: -0.0001

Data Index: 422822 (C4 (Web Text))

Max Activating Token Index: 459

Text #12

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0568. Min Act: -0.0001

Data Index: 1302524 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0554. Min Act: -0.0001

Data Index: 1028326 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0571. Min Act: -0.0000

Data Index: 500371 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0562. Min Act: -0.0001

Data Index: 418751 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0547. Min Act: -0.0002

Data Index: 714859 (C4 (Web Text))

Max Activating Token Index: 111

Text #17

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0554. Min Act: -0.0001

Data Index: 149620 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0562. Min Act: -0.0001

Data Index: 922756 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.0737. Min Range: -0.0737

Max Act: 0.0533. Min Act: -0.0001

Data Index: 1114136 (C4 (Web Text))

Max Activating Token Index: 198