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

Dataset: The Pile

Neuron 232 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: 0.1906. Min Range: -0.1906

Max Act: 0.1906. Min Act: -0.0000

Data Index: 389071 (The Pile)

Max Activating Token Index: 133

Text #1

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1859. Min Act: -0.0000

Data Index: 805249 (The Pile)

Max Activating Token Index: 803

Text #2

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1745. Min Act: -0.0000

Data Index: 281072 (The Pile)

Max Activating Token Index: 667

Text #3

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1769. Min Act: -0.0000

Data Index: 607845 (The Pile)

Max Activating Token Index: 358

Text #4

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1824. Min Act: -0.0000

Data Index: 620075 (The Pile)

Max Activating Token Index: 402

Text #5

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1588. Min Act: -0.0000

Data Index: 162241 (The Pile)

Max Activating Token Index: 689

Text #6

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1811. Min Act: -0.0000

Data Index: 672715 (The Pile)

Max Activating Token Index: 307

Text #7

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1678. Min Act: -0.0000

Data Index: 1059398 (The Pile)

Max Activating Token Index: 948

Text #8

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1813. Min Act: -0.0000

Data Index: 623413 (The Pile)

Max Activating Token Index: 743

Text #9

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1611. Min Act: -0.0000

Data Index: 211751 (The Pile)

Max Activating Token Index: 721

Text #10

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1545191 (The Pile)

Max Activating Token Index: 597

Text #11

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1599. Min Act: -0.0000

Data Index: 612191 (The Pile)

Max Activating Token Index: 1021

Text #12

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1166219 (The Pile)

Max Activating Token Index: 257

Text #13

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1589. Min Act: -0.0000

Data Index: 509969 (The Pile)

Max Activating Token Index: 740

Text #14

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1759. Min Act: -0.0000

Data Index: 393789 (The Pile)

Max Activating Token Index: 381

Text #15

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1470. Min Act: -0.0000

Data Index: 685581 (The Pile)

Max Activating Token Index: 742

Text #16

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1600. Min Act: -0.0000

Data Index: 1918457 (The Pile)

Max Activating Token Index: 522

Text #17

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1493. Min Act: -0.0000

Data Index: 343157 (The Pile)

Max Activating Token Index: 699

Text #18

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1633. Min Act: -0.0000

Data Index: 1098201 (The Pile)

Max Activating Token Index: 752

Text #19

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1591. Min Act: -0.0000

Data Index: 62842 (The Pile)

Max Activating Token Index: 341