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

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

Neuron 2709 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: 0.0736. Min Range: -0.0736

Max Act: 0.0736. Min Act: -0.0002

Data Index: 1257638 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0718. Min Act: -0.0002

Data Index: 746797 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0663. Min Act: -0.0002

Data Index: 489775 (C4 (Web Text))

Max Activating Token Index: 88

Text #3

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0667. Min Act: -0.0002

Data Index: 459215 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0638. Min Act: -0.0002

Data Index: 999168 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0583. Min Act: -0.0002

Data Index: 1092527 (C4 (Web Text))

Max Activating Token Index: 982

Text #6

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0584. Min Act: -0.0002

Data Index: 496103 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0539. Min Act: -0.0002

Data Index: 747849 (C4 (Web Text))

Max Activating Token Index: 828

Text #8

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1060061 (C4 (Web Text))

Max Activating Token Index: 145

Text #9

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0616. Min Act: -0.0002

Data Index: 204803 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0515. Min Act: -0.0002

Data Index: 801992 (C4 (Web Text))

Max Activating Token Index: 396

Text #11

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0453. Min Act: -0.0002

Data Index: 812380 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0602. Min Act: -0.0002

Data Index: 383035 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0545. Min Act: -0.0002

Data Index: 934555 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0554. Min Act: -0.0002

Data Index: 70083 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0582. Min Act: -0.0002

Data Index: 1300766 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1110253 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0578. Min Act: -0.0002

Data Index: 796006 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0524. Min Act: -0.0002

Data Index: 46216 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 0.0736. Min Range: -0.0736

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1032581 (C4 (Web Text))

Max Activating Token Index: 529