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

Dataset: The Pile

Neuron 1897 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: 0.1111. Min Range: -0.1111

Max Act: 0.1111. Min Act: -0.0000

Data Index: 854895 (The Pile)

Max Activating Token Index: 611

Text #1

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0900. Min Act: -0.0000

Data Index: 189460 (The Pile)

Max Activating Token Index: 259

Text #2

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0942. Min Act: -0.0000

Data Index: 1534964 (The Pile)

Max Activating Token Index: 78

Text #3

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0905. Min Act: -0.0000

Data Index: 540685 (The Pile)

Max Activating Token Index: 265

Text #4

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0843. Min Act: -0.0000

Data Index: 949737 (The Pile)

Max Activating Token Index: 344

Text #5

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0803. Min Act: -0.0000

Data Index: 1593890 (The Pile)

Max Activating Token Index: 385

Text #6

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0708. Min Act: -0.0000

Data Index: 794145 (The Pile)

Max Activating Token Index: 705

Text #7

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0761. Min Act: -0.0000

Data Index: 1774902 (The Pile)

Max Activating Token Index: 479

Text #8

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0833. Min Act: -0.0000

Data Index: 237102 (The Pile)

Max Activating Token Index: 329

Text #9

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0742. Min Act: -0.0000

Data Index: 83119 (The Pile)

Max Activating Token Index: 66

Text #10

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0795. Min Act: -0.0000

Data Index: 838481 (The Pile)

Max Activating Token Index: 981

Text #11

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0776. Min Act: -0.0000

Data Index: 110178 (The Pile)

Max Activating Token Index: 188

Text #12

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0754. Min Act: -0.0000

Data Index: 1211520 (The Pile)

Max Activating Token Index: 672

Text #13

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0815. Min Act: -0.0000

Data Index: 488792 (The Pile)

Max Activating Token Index: 744

Text #14

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0765. Min Act: -0.0000

Data Index: 613992 (The Pile)

Max Activating Token Index: 496

Text #15

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0806. Min Act: -0.0000

Data Index: 320764 (The Pile)

Max Activating Token Index: 980

Text #16

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0720. Min Act: -0.0000

Data Index: 740035 (The Pile)

Max Activating Token Index: 102

Text #17

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0778. Min Act: -0.0000

Data Index: 1215220 (The Pile)

Max Activating Token Index: 183

Text #18

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0724. Min Act: -0.0000

Data Index: 1910806 (The Pile)

Max Activating Token Index: 994

Text #19

Max Range: 0.1111. Min Range: -0.1111

Max Act: 0.0819. Min Act: -0.0000

Data Index: 1894500 (The Pile)

Max Activating Token Index: 224