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

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

Neuron 4587 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: 2.9191. Min Range: -2.9191

Max Act: 2.9191. Min Act: -0.0001

Data Index: 1207604 (C4 (Web Text))

Max Activating Token Index: 505

Text #1

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.4969. Min Act: -0.0001

Data Index: 349986 (C4 (Web Text))

Max Activating Token Index: 648

Text #2

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.5390. Min Act: -0.0000

Data Index: 1019550 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.1888. Min Act: -0.0000

Data Index: 308960 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.3893. Min Act: -0.0000

Data Index: 816516 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.0659. Min Act: -0.0000

Data Index: 925383 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.0714. Min Act: -0.0000

Data Index: 548970 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.2809. Min Act: -0.0000

Data Index: 914088 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.1341. Min Act: -0.0000

Data Index: 239783 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.0056. Min Act: -0.0000

Data Index: 369448 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.0484. Min Act: -0.0001

Data Index: 796726 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 2.9191. Min Range: -2.9191

Max Act: 1.9629. Min Act: -0.0000

Data Index: 868914 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.0586. Min Act: -0.0000

Data Index: 1211962 (C4 (Web Text))

Max Activating Token Index: 680

Text #13

Max Range: 2.9191. Min Range: -2.9191

Max Act: 1.8535. Min Act: -0.0000

Data Index: 847466 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 2.9191. Min Range: -2.9191

Max Act: 2.0424. Min Act: -0.0000

Data Index: 179635 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 2.9191. Min Range: -2.9191

Max Act: 1.8090. Min Act: -0.0001

Data Index: 196701 (C4 (Web Text))

Max Activating Token Index: 961

Text #16

Max Range: 2.9191. Min Range: -2.9191

Max Act: 1.8782. Min Act: -0.0001

Data Index: 932839 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 2.9191. Min Range: -2.9191

Max Act: 1.7803. Min Act: -0.0000

Data Index: 414829 (C4 (Web Text))

Max Activating Token Index: 848

Text #18

Max Range: 2.9191. Min Range: -2.9191

Max Act: 1.8649. Min Act: -0.0000

Data Index: 466655 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 2.9191. Min Range: -2.9191

Max Act: 1.9549. Min Act: -0.0000

Data Index: 720008 (C4 (Web Text))

Max Activating Token Index: 862