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

Dataset: The Pile

Neuron 4761 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5824. Min Range: -1.5824

Max Act: 1.5824. Min Act: -0.0000

Data Index: 1671853 (The Pile)

Max Activating Token Index: 807

Text #1

Max Range: 1.5824. Min Range: -1.5824

Max Act: 1.5035. Min Act: -0.0000

Data Index: 697481 (The Pile)

Max Activating Token Index: 842

Text #2

Max Range: 1.5824. Min Range: -1.5824

Max Act: 1.2508. Min Act: -0.0000

Data Index: 1503979 (The Pile)

Max Activating Token Index: 769

Text #3

Max Range: 1.5824. Min Range: -1.5824

Max Act: 1.1829. Min Act: -0.0000

Data Index: 263349 (The Pile)

Max Activating Token Index: 428

Text #4

Max Range: 1.5824. Min Range: -1.5824

Max Act: 1.1836. Min Act: -0.0000

Data Index: 212165 (The Pile)

Max Activating Token Index: 450

Text #5

Max Range: 1.5824. Min Range: -1.5824

Max Act: 1.1630. Min Act: -0.0000

Data Index: 1482496 (The Pile)

Max Activating Token Index: 346

Text #6

Max Range: 1.5824. Min Range: -1.5824

Max Act: 1.3452. Min Act: -0.0000

Data Index: 1754202 (The Pile)

Max Activating Token Index: 962

Text #7

Max Range: 1.5824. Min Range: -1.5824

Max Act: 1.1752. Min Act: -0.0000

Data Index: 820018 (The Pile)

Max Activating Token Index: 851

Text #8

Max Range: 1.5824. Min Range: -1.5824

Max Act: 1.2320. Min Act: -0.0000

Data Index: 1092891 (The Pile)

Max Activating Token Index: 777

Text #9

Max Range: 1.5824. Min Range: -1.5824

Max Act: 1.1594. Min Act: -0.0000

Data Index: 674705 (The Pile)

Max Activating Token Index: 491

Text #10

Max Range: 1.5824. Min Range: -1.5824

Max Act: 1.1164. Min Act: -0.0000

Data Index: 1389600 (The Pile)

Max Activating Token Index: 224

Text #11

Max Range: 1.5824. Min Range: -1.5824

Max Act: 1.1730. Min Act: -0.0000

Data Index: 1697859 (The Pile)

Max Activating Token Index: 538

Text #12

Max Range: 1.5824. Min Range: -1.5824

Max Act: 1.1025. Min Act: -0.0000

Data Index: 171362 (The Pile)

Max Activating Token Index: 964

Text #13

Max Range: 1.5824. Min Range: -1.5824

Max Act: 1.0582. Min Act: -0.0000

Data Index: 915699 (The Pile)

Max Activating Token Index: 400

Text #14

Max Range: 1.5824. Min Range: -1.5824

Max Act: 1.0645. Min Act: -0.0000

Data Index: 922713 (The Pile)

Max Activating Token Index: 661

Text #15

Max Range: 1.5824. Min Range: -1.5824

Max Act: 1.1269. Min Act: -0.0000

Data Index: 1656377 (The Pile)

Max Activating Token Index: 705

Text #16

Max Range: 1.5824. Min Range: -1.5824

Max Act: 1.1572. Min Act: -0.0000

Data Index: 1007237 (The Pile)

Max Activating Token Index: 341

Text #17

Max Range: 1.5824. Min Range: -1.5824

Max Act: 1.1155. Min Act: -0.0000

Data Index: 401890 (The Pile)

Max Activating Token Index: 832

Text #18

Max Range: 1.5824. Min Range: -1.5824

Max Act: 1.1141. Min Act: -0.0000

Data Index: 728273 (The Pile)

Max Activating Token Index: 592

Text #19

Max Range: 1.5824. Min Range: -1.5824

Max Act: 1.1002. Min Act: -0.0000

Data Index: 753700 (The Pile)

Max Activating Token Index: 213