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

Dataset: The Pile

Neuron 1625 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: 0.2210. Min Range: -0.2210

Max Act: 0.2104. Min Act: -0.0000

Data Index: 94902 (The Pile)

Max Activating Token Index: 513

Text #1

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1804. Min Act: -0.0000

Data Index: 9650 (The Pile)

Max Activating Token Index: 488

Text #2

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1853. Min Act: -0.0000

Data Index: 629777 (The Pile)

Max Activating Token Index: 590

Text #3

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1957. Min Act: -0.0000

Data Index: 1675302 (The Pile)

Max Activating Token Index: 550

Text #4

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.2144. Min Act: -0.0000

Data Index: 678560 (The Pile)

Max Activating Token Index: 1020

Text #5

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1843. Min Act: -0.0000

Data Index: 328470 (The Pile)

Max Activating Token Index: 971

Text #6

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1898. Min Act: -0.0000

Data Index: 1254809 (The Pile)

Max Activating Token Index: 761

Text #7

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.2210. Min Act: -0.0000

Data Index: 241533 (The Pile)

Max Activating Token Index: 641

Text #8

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1714. Min Act: -0.0000

Data Index: 1197791 (The Pile)

Max Activating Token Index: 744

Text #9

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1775. Min Act: -0.0000

Data Index: 564866 (The Pile)

Max Activating Token Index: 754

Text #10

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1663. Min Act: -0.0000

Data Index: 873987 (The Pile)

Max Activating Token Index: 478

Text #11

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1773. Min Act: -0.0000

Data Index: 990659 (The Pile)

Max Activating Token Index: 668

Text #12

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1801. Min Act: -0.0000

Data Index: 1402743 (The Pile)

Max Activating Token Index: 573

Text #13

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1638. Min Act: -0.0000

Data Index: 1885534 (The Pile)

Max Activating Token Index: 805

Text #14

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1935. Min Act: -0.0000

Data Index: 633127 (The Pile)

Max Activating Token Index: 946

Text #15

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1753. Min Act: -0.0000

Data Index: 1901200 (The Pile)

Max Activating Token Index: 852

Text #16

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1791. Min Act: -0.0000

Data Index: 1150296 (The Pile)

Max Activating Token Index: 338

Text #17

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1653. Min Act: -0.0000

Data Index: 1532281 (The Pile)

Max Activating Token Index: 939

Text #18

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1996. Min Act: -0.0000

Data Index: 196065 (The Pile)

Max Activating Token Index: 608

Text #19

Max Range: 0.2210. Min Range: -0.2210

Max Act: 0.1962. Min Act: -0.0000

Data Index: 319588 (The Pile)

Max Activating Token Index: 494