Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 636 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0563. Min Act: -0.0002

Data Index: 62281 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0584. Min Act: -0.0002

Data Index: 1482126 (Python Code)

Max Activating Token Index: 54

Text #2

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1406691 (Python Code)

Max Activating Token Index: 397

Text #3

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0618. Min Act: -0.0002

Data Index: 176563 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0518. Min Act: -0.0002

Data Index: 665541 (C4 (Web Text))

Max Activating Token Index: 803

Text #5

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0658. Min Act: -0.0002

Data Index: 570201 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1178517 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0667. Min Act: -0.0002

Data Index: 1173338 (C4 (Web Text))

Max Activating Token Index: 791

Text #8

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0478. Min Act: -0.0002

Data Index: 295646 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1202646 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0582. Min Act: -0.0002

Data Index: 98990 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0562. Min Act: -0.0002

Data Index: 977686 (C4 (Web Text))

Max Activating Token Index: 889

Text #12

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0601. Min Act: -0.0002

Data Index: 1305398 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0541. Min Act: -0.0002

Data Index: 741287 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1308784 (C4 (Web Text))

Max Activating Token Index: 678

Text #15

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0550. Min Act: -0.0002

Data Index: 418878 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0526. Min Act: -0.0002

Data Index: 890014 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0587. Min Act: -0.0002

Data Index: 252846 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0490. Min Act: -0.0002

Data Index: 1309744 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1652334 (Python Code)

Max Activating Token Index: 118