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

Dataset: The Pile

Neuron 1742 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: 1.3655. Min Range: -1.3655

Max Act: 1.2459. Min Act: -0.0000

Data Index: 48476 (The Pile)

Max Activating Token Index: 992

Text #1

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.1823. Min Act: -0.0000

Data Index: 1154998 (The Pile)

Max Activating Token Index: 677

Text #2

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.3655. Min Act: -0.0000

Data Index: 1769083 (The Pile)

Max Activating Token Index: 578

Text #3

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.1247. Min Act: -0.0000

Data Index: 314736 (The Pile)

Max Activating Token Index: 21

Text #4

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.0565. Min Act: -0.0000

Data Index: 1670032 (The Pile)

Max Activating Token Index: 948

Text #5

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.1076. Min Act: -0.0000

Data Index: 1007919 (The Pile)

Max Activating Token Index: 971

Text #6

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.0706. Min Act: -0.0000

Data Index: 297379 (The Pile)

Max Activating Token Index: 186

Text #7

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.0643. Min Act: -0.0000

Data Index: 781254 (The Pile)

Max Activating Token Index: 340

Text #8

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.0179. Min Act: -0.0000

Data Index: 548151 (The Pile)

Max Activating Token Index: 951

Text #9

Max Range: 1.3655. Min Range: -1.3655

Max Act: 0.9870. Min Act: -0.0000

Data Index: 1506823 (The Pile)

Max Activating Token Index: 663

Text #10

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.0898. Min Act: -0.0000

Data Index: 1304008 (The Pile)

Max Activating Token Index: 891

Text #11

Max Range: 1.3655. Min Range: -1.3655

Max Act: 0.9355. Min Act: -0.0000

Data Index: 396725 (The Pile)

Max Activating Token Index: 743

Text #12

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.0514. Min Act: -0.0000

Data Index: 186342 (The Pile)

Max Activating Token Index: 504

Text #13

Max Range: 1.3655. Min Range: -1.3655

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1577217 (The Pile)

Max Activating Token Index: 958

Text #14

Max Range: 1.3655. Min Range: -1.3655

Max Act: 0.7562. Min Act: -0.0000

Data Index: 295325 (The Pile)

Max Activating Token Index: 984

Text #15

Max Range: 1.3655. Min Range: -1.3655

Max Act: 1.0117. Min Act: -0.0000

Data Index: 983938 (The Pile)

Max Activating Token Index: 530

Text #16

Max Range: 1.3655. Min Range: -1.3655

Max Act: 0.9219. Min Act: -0.0000

Data Index: 1411760 (The Pile)

Max Activating Token Index: 566

Text #17

Max Range: 1.3655. Min Range: -1.3655

Max Act: 0.9212. Min Act: -0.0000

Data Index: 250142 (The Pile)

Max Activating Token Index: 24

Text #18

Max Range: 1.3655. Min Range: -1.3655

Max Act: 0.9299. Min Act: -0.0000

Data Index: 1706567 (The Pile)

Max Activating Token Index: 342

Text #19

Max Range: 1.3655. Min Range: -1.3655

Max Act: 0.8774. Min Act: -0.0000

Data Index: 1997256 (The Pile)

Max Activating Token Index: 444