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

Dataset: The Pile

Neuron 4272 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: 0.2172. Min Range: -0.2172

Max Act: 0.2172. Min Act: -0.0000

Data Index: 1351006 (The Pile)

Max Activating Token Index: 687

Text #1

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1991. Min Act: -0.0000

Data Index: 1827586 (The Pile)

Max Activating Token Index: 102

Text #2

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.2096. Min Act: -0.0000

Data Index: 1028909 (The Pile)

Max Activating Token Index: 998

Text #3

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1859. Min Act: -0.0000

Data Index: 57288 (The Pile)

Max Activating Token Index: 657

Text #4

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1772. Min Act: -0.0000

Data Index: 489557 (The Pile)

Max Activating Token Index: 636

Text #5

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.2024. Min Act: -0.0000

Data Index: 1867856 (The Pile)

Max Activating Token Index: 958

Text #6

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1938. Min Act: -0.0000

Data Index: 70124 (The Pile)

Max Activating Token Index: 503

Text #7

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1871. Min Act: -0.0000

Data Index: 652639 (The Pile)

Max Activating Token Index: 57

Text #8

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1759. Min Act: -0.0000

Data Index: 904270 (The Pile)

Max Activating Token Index: 884

Text #9

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1803. Min Act: -0.0000

Data Index: 541841 (The Pile)

Max Activating Token Index: 1001

Text #10

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1685. Min Act: -0.0000

Data Index: 1595230 (The Pile)

Max Activating Token Index: 781

Text #11

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1857. Min Act: -0.0000

Data Index: 669015 (The Pile)

Max Activating Token Index: 291

Text #12

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1664. Min Act: -0.0000

Data Index: 168780 (The Pile)

Max Activating Token Index: 604

Text #13

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1398446 (The Pile)

Max Activating Token Index: 248

Text #14

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1959. Min Act: -0.0000

Data Index: 1250260 (The Pile)

Max Activating Token Index: 202

Text #15

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1899. Min Act: -0.0000

Data Index: 245237 (The Pile)

Max Activating Token Index: 166

Text #16

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1823. Min Act: -0.0000

Data Index: 1437252 (The Pile)

Max Activating Token Index: 989

Text #17

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1949. Min Act: -0.0000

Data Index: 911450 (The Pile)

Max Activating Token Index: 750

Text #18

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1822. Min Act: -0.0000

Data Index: 1642104 (The Pile)

Max Activating Token Index: 675

Text #19

Max Range: 0.2172. Min Range: -0.2172

Max Act: 0.1840. Min Act: -0.0000

Data Index: 1335841 (The Pile)

Max Activating Token Index: 922