Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2773 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0910. Min Act: -0.0002

Data Index: 1269276 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0704. Min Act: -0.0002

Data Index: 664063 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0714. Min Act: -0.0002

Data Index: 1349079 (C4 (Web Text))

Max Activating Token Index: 105

Text #3

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0680. Min Act: -0.0002

Data Index: 980357 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0704. Min Act: -0.0002

Data Index: 1115725 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0649. Min Act: -0.0002

Data Index: 381646 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0657. Min Act: -0.0002

Data Index: 752953 (C4 (Web Text))

Max Activating Token Index: 354

Text #7

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0680. Min Act: -0.0002

Data Index: 472112 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0626. Min Act: -0.0002

Data Index: 1047220 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0602. Min Act: -0.0002

Data Index: 65327 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0635. Min Act: -0.0002

Data Index: 54226 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0611. Min Act: -0.0002

Data Index: 113221 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1309777 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0603. Min Act: -0.0002

Data Index: 145379 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0598. Min Act: -0.0002

Data Index: 678154 (C4 (Web Text))

Max Activating Token Index: 686

Text #15

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0566. Min Act: -0.0002

Data Index: 311870 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0601. Min Act: -0.0002

Data Index: 521209 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0583. Min Act: -0.0002

Data Index: 256 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0559. Min Act: -0.0002

Data Index: 1016805 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0573. Min Act: -0.0002

Data Index: 689931 (C4 (Web Text))

Max Activating Token Index: 647