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

Dataset: The Pile

Neuron 1813 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2449. Min Act: -0.0000

Data Index: 1026437 (The Pile)

Max Activating Token Index: 165

Text #1

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.2462. Min Act: -0.0000

Data Index: 264978 (The Pile)

Max Activating Token Index: 889

Text #2

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1911. Min Act: -0.0000

Data Index: 1259070 (The Pile)

Max Activating Token Index: 861

Text #3

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1877. Min Act: -0.0000

Data Index: 467406 (The Pile)

Max Activating Token Index: 383

Text #4

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1859. Min Act: -0.0000

Data Index: 1045989 (The Pile)

Max Activating Token Index: 547

Text #5

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1686. Min Act: -0.0000

Data Index: 141047 (The Pile)

Max Activating Token Index: 753

Text #6

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1874. Min Act: -0.0000

Data Index: 1206675 (The Pile)

Max Activating Token Index: 988

Text #7

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1791. Min Act: -0.0000

Data Index: 1711427 (The Pile)

Max Activating Token Index: 44

Text #8

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1860. Min Act: -0.0000

Data Index: 1455199 (The Pile)

Max Activating Token Index: 1019

Text #9

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1844. Min Act: -0.0000

Data Index: 1372920 (The Pile)

Max Activating Token Index: 333

Text #10

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1886. Min Act: -0.0000

Data Index: 1478953 (The Pile)

Max Activating Token Index: 198

Text #11

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1658. Min Act: -0.0000

Data Index: 81378 (The Pile)

Max Activating Token Index: 539

Text #12

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1706. Min Act: -0.0000

Data Index: 702721 (The Pile)

Max Activating Token Index: 184

Text #13

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1823. Min Act: -0.0000

Data Index: 902472 (The Pile)

Max Activating Token Index: 732

Text #14

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1782. Min Act: -0.0000

Data Index: 405820 (The Pile)

Max Activating Token Index: 430

Text #15

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1729. Min Act: -0.0000

Data Index: 1669375 (The Pile)

Max Activating Token Index: 999

Text #16

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1657. Min Act: -0.0000

Data Index: 1346550 (The Pile)

Max Activating Token Index: 222

Text #17

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1747. Min Act: -0.0000

Data Index: 1740177 (The Pile)

Max Activating Token Index: 564

Text #18

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1659. Min Act: -0.0000

Data Index: 346135 (The Pile)

Max Activating Token Index: 395

Text #19

Max Range: 0.2462. Min Range: -0.2462

Max Act: 0.1603. Min Act: -0.0000

Data Index: 68318 (The Pile)

Max Activating Token Index: 898