Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3848 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0864. Min Range: -1.0864

Max Act: 1.0218. Min Act: -0.0000

Data Index: 723469 (The Pile)

Max Activating Token Index: 720

Text #1

Max Range: 1.0864. Min Range: -1.0864

Max Act: 1.0116. Min Act: -0.0000

Data Index: 790759 (The Pile)

Max Activating Token Index: 982

Text #2

Max Range: 1.0864. Min Range: -1.0864

Max Act: 1.0586. Min Act: -0.0000

Data Index: 1013712 (The Pile)

Max Activating Token Index: 939

Text #3

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.9175. Min Act: -0.0000

Data Index: 294881 (The Pile)

Max Activating Token Index: 808

Text #4

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.7866. Min Act: -0.0000

Data Index: 930633 (The Pile)

Max Activating Token Index: 808

Text #5

Max Range: 1.0864. Min Range: -1.0864

Max Act: 1.0784. Min Act: -0.0000

Data Index: 1629816 (The Pile)

Max Activating Token Index: 188

Text #6

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.9363. Min Act: -0.0000

Data Index: 835961 (The Pile)

Max Activating Token Index: 962

Text #7

Max Range: 1.0864. Min Range: -1.0864

Max Act: 1.0864. Min Act: -0.0000

Data Index: 535057 (The Pile)

Max Activating Token Index: 875

Text #8

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.9193. Min Act: -0.0000

Data Index: 1106865 (The Pile)

Max Activating Token Index: 489

Text #9

Max Range: 1.0864. Min Range: -1.0864

Max Act: 1.0063. Min Act: -0.0000

Data Index: 475703 (The Pile)

Max Activating Token Index: 744

Text #10

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.8876. Min Act: -0.0000

Data Index: 1955663 (The Pile)

Max Activating Token Index: 739

Text #11

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.9708. Min Act: -0.0000

Data Index: 584798 (The Pile)

Max Activating Token Index: 210

Text #12

Max Range: 1.0864. Min Range: -1.0864

Max Act: 1.0245. Min Act: -0.0000

Data Index: 73656 (The Pile)

Max Activating Token Index: 673

Text #13

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.9095. Min Act: -0.0000

Data Index: 1524951 (The Pile)

Max Activating Token Index: 875

Text #14

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.9014. Min Act: -0.0000

Data Index: 1253423 (The Pile)

Max Activating Token Index: 690

Text #15

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.8668. Min Act: -0.0000

Data Index: 93911 (The Pile)

Max Activating Token Index: 564

Text #16

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.7864. Min Act: -0.0000

Data Index: 574564 (The Pile)

Max Activating Token Index: 607

Text #17

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.9452. Min Act: -0.0000

Data Index: 315461 (The Pile)

Max Activating Token Index: 1020

Text #18

Max Range: 1.0864. Min Range: -1.0864

Max Act: 1.0577. Min Act: -0.0000

Data Index: 1013424 (The Pile)

Max Activating Token Index: 856

Text #19

Max Range: 1.0864. Min Range: -1.0864

Max Act: 0.9385. Min Act: -0.0000

Data Index: 1674610 (The Pile)

Max Activating Token Index: 856