Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1269 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1918. Min Act: -0.0000

Data Index: 861506 (The Pile)

Max Activating Token Index: 59

Text #1

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1972. Min Act: -0.0000

Data Index: 1946876 (The Pile)

Max Activating Token Index: 15

Text #2

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1967. Min Act: -0.0000

Data Index: 388589 (The Pile)

Max Activating Token Index: 480

Text #3

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1895. Min Act: -0.0000

Data Index: 738325 (The Pile)

Max Activating Token Index: 512

Text #4

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1859. Min Act: -0.0000

Data Index: 1467199 (The Pile)

Max Activating Token Index: 44

Text #5

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1929. Min Act: -0.0000

Data Index: 20640 (The Pile)

Max Activating Token Index: 117

Text #6

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1795. Min Act: 0.0000

Data Index: 571170 (The Pile)

Max Activating Token Index: 180

Text #7

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1911. Min Act: -0.0000

Data Index: 1952135 (The Pile)

Max Activating Token Index: 697

Text #8

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1816. Min Act: -0.0000

Data Index: 1066787 (The Pile)

Max Activating Token Index: 81

Text #9

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1885. Min Act: -0.0000

Data Index: 1617771 (The Pile)

Max Activating Token Index: 270

Text #10

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1873. Min Act: -0.0000

Data Index: 1752929 (The Pile)

Max Activating Token Index: 538

Text #11

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1747. Min Act: -0.0000

Data Index: 1085864 (The Pile)

Max Activating Token Index: 228

Text #12

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1874. Min Act: -0.0000

Data Index: 726798 (The Pile)

Max Activating Token Index: 612

Text #13

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1736. Min Act: -0.0000

Data Index: 1126250 (The Pile)

Max Activating Token Index: 831

Text #14

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1782. Min Act: -0.0000

Data Index: 1390681 (The Pile)

Max Activating Token Index: 871

Text #15

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1700. Min Act: -0.0000

Data Index: 1769390 (The Pile)

Max Activating Token Index: 303

Text #16

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1771. Min Act: -0.0000

Data Index: 1589072 (The Pile)

Max Activating Token Index: 934

Text #17

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1809. Min Act: 0.0000

Data Index: 1573374 (The Pile)

Max Activating Token Index: 132

Text #18

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1787. Min Act: 0.0000

Data Index: 148608 (The Pile)

Max Activating Token Index: 811

Text #19

Max Range: 0.1972. Min Range: -0.1972

Max Act: 0.1748. Min Act: 0.0000

Data Index: 1207536 (The Pile)

Max Activating Token Index: 714