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

Dataset: The Pile

Neuron 1313 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: 0.2811. Min Range: -0.2811

Max Act: 0.2811. Min Act: -0.0000

Data Index: 910153 (The Pile)

Max Activating Token Index: 525

Text #1

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2469. Min Act: -0.0000

Data Index: 1760899 (The Pile)

Max Activating Token Index: 248

Text #2

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2190. Min Act: -0.0000

Data Index: 362191 (The Pile)

Max Activating Token Index: 830

Text #3

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2029. Min Act: -0.0000

Data Index: 860798 (The Pile)

Max Activating Token Index: 585

Text #4

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2018. Min Act: -0.0000

Data Index: 6727 (The Pile)

Max Activating Token Index: 662

Text #5

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1947. Min Act: -0.0000

Data Index: 1959127 (The Pile)

Max Activating Token Index: 350

Text #6

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1916. Min Act: -0.0000

Data Index: 755269 (The Pile)

Max Activating Token Index: 812

Text #7

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1778. Min Act: -0.0000

Data Index: 1774195 (The Pile)

Max Activating Token Index: 730

Text #8

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2035. Min Act: -0.0000

Data Index: 1011328 (The Pile)

Max Activating Token Index: 556

Text #9

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1835. Min Act: -0.0000

Data Index: 1505387 (The Pile)

Max Activating Token Index: 76

Text #10

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1866. Min Act: -0.0000

Data Index: 1836062 (The Pile)

Max Activating Token Index: 736

Text #11

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1810. Min Act: -0.0000

Data Index: 413646 (The Pile)

Max Activating Token Index: 981

Text #12

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2011. Min Act: -0.0000

Data Index: 1193959 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1924. Min Act: -0.0000

Data Index: 180869 (The Pile)

Max Activating Token Index: 237

Text #14

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2018. Min Act: -0.0000

Data Index: 1848517 (The Pile)

Max Activating Token Index: 631

Text #15

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1886. Min Act: -0.0000

Data Index: 1207411 (The Pile)

Max Activating Token Index: 201

Text #16

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1876. Min Act: -0.0000

Data Index: 1962760 (The Pile)

Max Activating Token Index: 920

Text #17

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1884. Min Act: -0.0000

Data Index: 531137 (The Pile)

Max Activating Token Index: 569

Text #18

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1879. Min Act: -0.0000

Data Index: 1367720 (The Pile)

Max Activating Token Index: 699

Text #19

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1939. Min Act: -0.0000

Data Index: 1908636 (The Pile)

Max Activating Token Index: 135