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

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

Neuron 92 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: 0.0606. Min Range: -0.0606

Max Act: 0.0603. Min Act: -0.0003

Data Index: 560657 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0571. Min Act: -0.0003

Data Index: 344158 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0606. Min Act: -0.0003

Data Index: 516178 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0563. Min Act: -0.0003

Data Index: 200665 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0518. Min Act: -0.0003

Data Index: 1125429 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0534. Min Act: -0.0003

Data Index: 68818 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0527. Min Act: -0.0003

Data Index: 1072669 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0539. Min Act: -0.0003

Data Index: 507126 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0509. Min Act: -0.0003

Data Index: 36136 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0502. Min Act: -0.0003

Data Index: 1050552 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0505. Min Act: -0.0003

Data Index: 440059 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0560. Min Act: -0.0003

Data Index: 889558 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0536. Min Act: -0.0003

Data Index: 350288 (C4 (Web Text))

Max Activating Token Index: 937

Text #13

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0537. Min Act: -0.0003

Data Index: 675655 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0505. Min Act: -0.0003

Data Index: 1034932 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0528. Min Act: -0.0003

Data Index: 1341699 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0492. Min Act: -0.0003

Data Index: 500955 (C4 (Web Text))

Max Activating Token Index: 436

Text #17

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0511. Min Act: -0.0003

Data Index: 3135 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0535. Min Act: -0.0003

Data Index: 1065944 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0533. Min Act: -0.0003

Data Index: 240859 (C4 (Web Text))

Max Activating Token Index: 392