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

Dataset: The Pile

Neuron 4956 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: 0.1026. Min Range: -0.1026

Max Act: 0.1026. Min Act: -0.0000

Data Index: 1091663 (The Pile)

Max Activating Token Index: 39

Text #1

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0977. Min Act: -0.0000

Data Index: 206426 (The Pile)

Max Activating Token Index: 393

Text #2

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0902. Min Act: -0.0000

Data Index: 898490 (The Pile)

Max Activating Token Index: 633

Text #3

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0990. Min Act: -0.0000

Data Index: 28559 (The Pile)

Max Activating Token Index: 398

Text #4

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0905. Min Act: -0.0000

Data Index: 925727 (The Pile)

Max Activating Token Index: 534

Text #5

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0874. Min Act: -0.0000

Data Index: 197870 (The Pile)

Max Activating Token Index: 831

Text #6

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0901. Min Act: -0.0000

Data Index: 1038177 (The Pile)

Max Activating Token Index: 456

Text #7

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0827. Min Act: -0.0000

Data Index: 1220573 (The Pile)

Max Activating Token Index: 677

Text #8

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0831. Min Act: -0.0000

Data Index: 1627476 (The Pile)

Max Activating Token Index: 473

Text #9

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0872. Min Act: -0.0000

Data Index: 119437 (The Pile)

Max Activating Token Index: 703

Text #10

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0844. Min Act: -0.0000

Data Index: 815802 (The Pile)

Max Activating Token Index: 784

Text #11

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0838. Min Act: -0.0000

Data Index: 1824474 (The Pile)

Max Activating Token Index: 594

Text #12

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0928. Min Act: -0.0000

Data Index: 1318177 (The Pile)

Max Activating Token Index: 781

Text #13

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0820. Min Act: -0.0000

Data Index: 1191022 (The Pile)

Max Activating Token Index: 631

Text #14

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0816. Min Act: -0.0000

Data Index: 1843509 (The Pile)

Max Activating Token Index: 538

Text #15

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0776. Min Act: -0.0000

Data Index: 800241 (The Pile)

Max Activating Token Index: 44

Text #16

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0780. Min Act: -0.0000

Data Index: 482351 (The Pile)

Max Activating Token Index: 462

Text #17

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0789. Min Act: -0.0000

Data Index: 1690404 (The Pile)

Max Activating Token Index: 59

Text #18

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0812. Min Act: -0.0000

Data Index: 170300 (The Pile)

Max Activating Token Index: 73

Text #19

Max Range: 0.1026. Min Range: -0.1026

Max Act: 0.0795. Min Act: -0.0000

Data Index: 1208074 (The Pile)

Max Activating Token Index: 303