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

Dataset: The Pile

Neuron 1661 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: 0.2955. Min Range: -0.2955

Max Act: 0.2955. Min Act: -0.0000

Data Index: 1275434 (The Pile)

Max Activating Token Index: 711

Text #1

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2377. Min Act: -0.0000

Data Index: 1427265 (The Pile)

Max Activating Token Index: 597

Text #2

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2255. Min Act: -0.0000

Data Index: 1613071 (The Pile)

Max Activating Token Index: 326

Text #3

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2397. Min Act: -0.0000

Data Index: 510797 (The Pile)

Max Activating Token Index: 619

Text #4

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2270. Min Act: -0.0000

Data Index: 154663 (The Pile)

Max Activating Token Index: 24

Text #5

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2174. Min Act: -0.0000

Data Index: 229537 (The Pile)

Max Activating Token Index: 425

Text #6

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2260. Min Act: -0.0000

Data Index: 1357414 (The Pile)

Max Activating Token Index: 517

Text #7

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2113. Min Act: -0.0000

Data Index: 1343380 (The Pile)

Max Activating Token Index: 59

Text #8

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2072. Min Act: -0.0000

Data Index: 1760007 (The Pile)

Max Activating Token Index: 301

Text #9

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1725. Min Act: -0.0000

Data Index: 835075 (The Pile)

Max Activating Token Index: 907

Text #10

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1999. Min Act: -0.0000

Data Index: 978081 (The Pile)

Max Activating Token Index: 899

Text #11

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1991. Min Act: -0.0000

Data Index: 1488915 (The Pile)

Max Activating Token Index: 637

Text #12

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1882. Min Act: -0.0000

Data Index: 1401174 (The Pile)

Max Activating Token Index: 187

Text #13

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1859. Min Act: -0.0000

Data Index: 1454280 (The Pile)

Max Activating Token Index: 423

Text #14

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1890. Min Act: -0.0000

Data Index: 480854 (The Pile)

Max Activating Token Index: 105

Text #15

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1873. Min Act: -0.0000

Data Index: 1626210 (The Pile)

Max Activating Token Index: 333

Text #16

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1780. Min Act: -0.0000

Data Index: 1822909 (The Pile)

Max Activating Token Index: 801

Text #17

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1958381 (The Pile)

Max Activating Token Index: 458

Text #18

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1831. Min Act: -0.0000

Data Index: 700573 (The Pile)

Max Activating Token Index: 527

Text #19

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1829. Min Act: -0.0000

Data Index: 1887902 (The Pile)

Max Activating Token Index: 16