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

Dataset: The Pile

Neuron 336 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2955. Min Act: -0.0000

Data Index: 1500281 (The Pile)

Max Activating Token Index: 955

Text #1

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2582. Min Act: -0.0000

Data Index: 1111894 (The Pile)

Max Activating Token Index: 271

Text #2

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1224528 (The Pile)

Max Activating Token Index: 168

Text #3

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1867003 (The Pile)

Max Activating Token Index: 825

Text #4

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1984. Min Act: -0.0000

Data Index: 573080 (The Pile)

Max Activating Token Index: 764

Text #5

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2119. Min Act: -0.0000

Data Index: 708310 (The Pile)

Max Activating Token Index: 241

Text #6

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2035. Min Act: -0.0000

Data Index: 1758630 (The Pile)

Max Activating Token Index: 314

Text #7

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1966. Min Act: -0.0000

Data Index: 500305 (The Pile)

Max Activating Token Index: 644

Text #8

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1893. Min Act: -0.0000

Data Index: 800496 (The Pile)

Max Activating Token Index: 496

Text #9

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1932. Min Act: -0.0000

Data Index: 1392823 (The Pile)

Max Activating Token Index: 406

Text #10

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1880. Min Act: -0.0000

Data Index: 1774220 (The Pile)

Max Activating Token Index: 353

Text #11

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1878. Min Act: -0.0000

Data Index: 1745535 (The Pile)

Max Activating Token Index: 134

Text #12

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1774. Min Act: -0.0000

Data Index: 140203 (The Pile)

Max Activating Token Index: 448

Text #13

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1870. Min Act: -0.0000

Data Index: 770264 (The Pile)

Max Activating Token Index: 510

Text #14

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.2098. Min Act: -0.0000

Data Index: 360470 (The Pile)

Max Activating Token Index: 608

Text #15

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1638. Min Act: -0.0000

Data Index: 926948 (The Pile)

Max Activating Token Index: 167

Text #16

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1571. Min Act: -0.0000

Data Index: 452544 (The Pile)

Max Activating Token Index: 450

Text #17

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1626. Min Act: -0.0000

Data Index: 1737485 (The Pile)

Max Activating Token Index: 232

Text #18

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1619. Min Act: -0.0000

Data Index: 1644997 (The Pile)

Max Activating Token Index: 682

Text #19

Max Range: 0.2955. Min Range: -0.2955

Max Act: 0.1667. Min Act: -0.0000

Data Index: 1660572 (The Pile)

Max Activating Token Index: 694