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

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

Neuron 953 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: 0.0754. Min Range: -0.0754

Max Act: 0.0754. Min Act: -0.0005

Data Index: 838335 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0653. Min Act: -0.0005

Data Index: 145903 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0656. Min Act: -0.0005

Data Index: 458264 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0654. Min Act: -0.0005

Data Index: 191611 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0668. Min Act: -0.0005

Data Index: 333009 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0614. Min Act: -0.0005

Data Index: 228211 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0641. Min Act: -0.0005

Data Index: 810582 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0605. Min Act: -0.0005

Data Index: 562719 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0614. Min Act: -0.0005

Data Index: 176378 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0626. Min Act: -0.0005

Data Index: 1005602 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0584. Min Act: -0.0005

Data Index: 315045 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0606. Min Act: -0.0005

Data Index: 923706 (C4 (Web Text))

Max Activating Token Index: 665

Text #12

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0597. Min Act: -0.0005

Data Index: 766629 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0614. Min Act: -0.0005

Data Index: 724839 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0586. Min Act: -0.0005

Data Index: 1121519 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0591. Min Act: -0.0005

Data Index: 1164355 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0577. Min Act: -0.0005

Data Index: 1005780 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0574. Min Act: -0.0005

Data Index: 837748 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0552. Min Act: -0.0005

Data Index: 499929 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 0.0754. Min Range: -0.0754

Max Act: 0.0570. Min Act: -0.0005

Data Index: 343459 (C4 (Web Text))

Max Activating Token Index: 727