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

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

Neuron 266 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0804. Min Act: -0.0005

Data Index: 669169 (C4 (Web Text))

Max Activating Token Index: 872

Text #1

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0760. Min Act: -0.0005

Data Index: 318246 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0769. Min Act: -0.0005

Data Index: 338628 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0746. Min Act: -0.0005

Data Index: 1110442 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0743. Min Act: -0.0005

Data Index: 260711 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0743. Min Act: -0.0005

Data Index: 822120 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0718. Min Act: -0.0005

Data Index: 428312 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0679. Min Act: -0.0005

Data Index: 562504 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0715. Min Act: -0.0005

Data Index: 759837 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0724. Min Act: -0.0005

Data Index: 946253 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0687. Min Act: -0.0005

Data Index: 373289 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0644. Min Act: -0.0005

Data Index: 1060376 (C4 (Web Text))

Max Activating Token Index: 834

Text #12

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0708. Min Act: -0.0005

Data Index: 1036012 (C4 (Web Text))

Max Activating Token Index: 493

Text #13

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0654. Min Act: -0.0005

Data Index: 943595 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0692. Min Act: -0.0005

Data Index: 609326 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0698. Min Act: -0.0005

Data Index: 609130 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0671. Min Act: -0.0005

Data Index: 946423 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0693. Min Act: -0.0005

Data Index: 510605 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0665. Min Act: -0.0005

Data Index: 871911 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 0.0804. Min Range: -0.0804

Max Act: 0.0668. Min Act: -0.0005

Data Index: 644070 (C4 (Web Text))

Max Activating Token Index: 512