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

Dataset: The Pile

Neuron 4756 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.3375. Min Act: -0.0000

Data Index: 1215576 (The Pile)

Max Activating Token Index: 584

Text #1

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2889. Min Act: -0.0000

Data Index: 441918 (The Pile)

Max Activating Token Index: 312

Text #2

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2038. Min Act: -0.0000

Data Index: 492886 (The Pile)

Max Activating Token Index: 490

Text #3

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.2123. Min Act: -0.0000

Data Index: 607261 (The Pile)

Max Activating Token Index: 818

Text #4

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1061151 (The Pile)

Max Activating Token Index: 45

Text #5

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.1927. Min Act: -0.0000

Data Index: 1799214 (The Pile)

Max Activating Token Index: 565

Text #6

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1169626 (The Pile)

Max Activating Token Index: 420

Text #7

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.1904. Min Act: -0.0000

Data Index: 1503179 (The Pile)

Max Activating Token Index: 458

Text #8

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.1896. Min Act: -0.0000

Data Index: 1252382 (The Pile)

Max Activating Token Index: 614

Text #9

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1788233 (The Pile)

Max Activating Token Index: 816

Text #10

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.1855. Min Act: -0.0000

Data Index: 758534 (The Pile)

Max Activating Token Index: 118

Text #11

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.1829. Min Act: -0.0000

Data Index: 968444 (The Pile)

Max Activating Token Index: 381

Text #12

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.1833. Min Act: -0.0000

Data Index: 995882 (The Pile)

Max Activating Token Index: 598

Text #13

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.1808. Min Act: -0.0000

Data Index: 637158 (The Pile)

Max Activating Token Index: 317

Text #14

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1406836 (The Pile)

Max Activating Token Index: 458

Text #15

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.1835. Min Act: -0.0000

Data Index: 1451473 (The Pile)

Max Activating Token Index: 703

Text #16

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.1639. Min Act: -0.0000

Data Index: 1000697 (The Pile)

Max Activating Token Index: 925

Text #17

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.1733. Min Act: -0.0000

Data Index: 269989 (The Pile)

Max Activating Token Index: 222

Text #18

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.1696. Min Act: -0.0000

Data Index: 494138 (The Pile)

Max Activating Token Index: 441

Text #19

Max Range: 0.3375. Min Range: -0.3375

Max Act: 0.1761. Min Act: -0.0000

Data Index: 1259672 (The Pile)

Max Activating Token Index: 227