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

Dataset: The Pile

Neuron 1126 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6927. Min Act: -0.0000

Data Index: 1313203 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6342. Min Act: -0.0000

Data Index: 490811 (The Pile)

Max Activating Token Index: 943

Text #2

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5953. Min Act: -0.0000

Data Index: 1378038 (The Pile)

Max Activating Token Index: 779

Text #3

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.6071. Min Act: -0.0000

Data Index: 180236 (The Pile)

Max Activating Token Index: 665

Text #4

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5952. Min Act: -0.0000

Data Index: 315239 (The Pile)

Max Activating Token Index: 805

Text #5

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5818. Min Act: -0.0000

Data Index: 935382 (The Pile)

Max Activating Token Index: 582

Text #6

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5739. Min Act: -0.0000

Data Index: 1283799 (The Pile)

Max Activating Token Index: 215

Text #7

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5578. Min Act: -0.0000

Data Index: 972797 (The Pile)

Max Activating Token Index: 154

Text #8

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5459. Min Act: -0.0000

Data Index: 1348573 (The Pile)

Max Activating Token Index: 735

Text #9

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5380. Min Act: -0.0000

Data Index: 917861 (The Pile)

Max Activating Token Index: 231

Text #10

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1452398 (The Pile)

Max Activating Token Index: 301

Text #11

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5387. Min Act: -0.0000

Data Index: 1073347 (The Pile)

Max Activating Token Index: 966

Text #12

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5136. Min Act: -0.0000

Data Index: 107703 (The Pile)

Max Activating Token Index: 781

Text #13

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5649. Min Act: -0.0000

Data Index: 88493 (The Pile)

Max Activating Token Index: 818

Text #14

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5372. Min Act: -0.0000

Data Index: 1280559 (The Pile)

Max Activating Token Index: 454

Text #15

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5040. Min Act: -0.0000

Data Index: 1800041 (The Pile)

Max Activating Token Index: 666

Text #16

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5651. Min Act: -0.0000

Data Index: 610797 (The Pile)

Max Activating Token Index: 689

Text #17

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5214. Min Act: -0.0000

Data Index: 1732061 (The Pile)

Max Activating Token Index: 762

Text #18

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.5045. Min Act: -0.0000

Data Index: 1084733 (The Pile)

Max Activating Token Index: 230

Text #19

Max Range: 0.6927. Min Range: -0.6927

Max Act: 0.4703. Min Act: -0.0000

Data Index: 1384847 (The Pile)

Max Activating Token Index: 13