Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2605 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.1235. Min Act: -0.0003

Data Index: 506203 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0867. Min Act: -0.0003

Data Index: 990511 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0901. Min Act: -0.0003

Data Index: 657633 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0860. Min Act: -0.0003

Data Index: 51768 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0917. Min Act: -0.0003

Data Index: 778740 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0829. Min Act: -0.0003

Data Index: 520863 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0929. Min Act: -0.0003

Data Index: 409648 (C4 (Web Text))

Max Activating Token Index: 579

Text #7

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0823. Min Act: -0.0003

Data Index: 1352723 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0859. Min Act: -0.0003

Data Index: 877422 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0848. Min Act: -0.0003

Data Index: 228132 (C4 (Web Text))

Max Activating Token Index: 82

Text #10

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0847. Min Act: -0.0003

Data Index: 122336 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0775. Min Act: -0.0003

Data Index: 1136932 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0898. Min Act: -0.0003

Data Index: 629744 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0785. Min Act: -0.0003

Data Index: 80853 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0846. Min Act: -0.0003

Data Index: 913361 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0828. Min Act: -0.0003

Data Index: 735721 (C4 (Web Text))

Max Activating Token Index: 63

Text #16

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0795. Min Act: -0.0003

Data Index: 827964 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0790. Min Act: -0.0003

Data Index: 175113 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0764. Min Act: -0.0003

Data Index: 963852 (C4 (Web Text))

Max Activating Token Index: 248

Text #19

Max Range: 0.1235. Min Range: -0.1235

Max Act: 0.0788. Min Act: -0.0003

Data Index: 531540 (C4 (Web Text))

Max Activating Token Index: 215