Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 989 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0667. Min Act: -0.0001

Data Index: 36449 (C4 (Web Text))

Max Activating Token Index: 247

Text #1

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0659. Min Act: -0.0002

Data Index: 930162 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0652. Min Act: -0.0001

Data Index: 21798 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0664. Min Act: -0.0002

Data Index: 459041 (C4 (Web Text))

Max Activating Token Index: 313

Text #4

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0638. Min Act: -0.0002

Data Index: 290620 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0645. Min Act: -0.0002

Data Index: 981175 (C4 (Web Text))

Max Activating Token Index: 627

Text #6

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0639. Min Act: -0.0001

Data Index: 934740 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0642. Min Act: -0.0001

Data Index: 1197883 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0657. Min Act: -0.0002

Data Index: 778530 (C4 (Web Text))

Max Activating Token Index: 1008

Text #9

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0623. Min Act: -0.0002

Data Index: 52031 (C4 (Web Text))

Max Activating Token Index: 183

Text #10

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0618. Min Act: -0.0002

Data Index: 458057 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0618. Min Act: -0.0002

Data Index: 172621 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0621. Min Act: -0.0002

Data Index: 216784 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0596. Min Act: -0.0002

Data Index: 566510 (C4 (Web Text))

Max Activating Token Index: 845

Text #14

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0598. Min Act: -0.0002

Data Index: 890169 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0591. Min Act: -0.0002

Data Index: 179471 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0587. Min Act: -0.0001

Data Index: 459285 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0589. Min Act: -0.0002

Data Index: 1182583 (C4 (Web Text))

Max Activating Token Index: 257

Text #18

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0599. Min Act: -0.0002

Data Index: 108278 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.0667. Min Range: -0.0667

Max Act: 0.0593. Min Act: -0.0001

Data Index: 28716 (C4 (Web Text))

Max Activating Token Index: 956