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

Dataset: The Pile

Neuron 429 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: 0.2630. Min Range: -0.2630

Max Act: 0.2630. Min Act: -0.0000

Data Index: 1591489 (The Pile)

Max Activating Token Index: 1001

Text #1

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.2471. Min Act: -0.0000

Data Index: 1236674 (The Pile)

Max Activating Token Index: 30

Text #2

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.2309. Min Act: -0.0000

Data Index: 1231853 (The Pile)

Max Activating Token Index: 261

Text #3

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.2273. Min Act: -0.0000

Data Index: 1395917 (The Pile)

Max Activating Token Index: 393

Text #4

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1756301 (The Pile)

Max Activating Token Index: 732

Text #5

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.2248. Min Act: -0.0000

Data Index: 735842 (The Pile)

Max Activating Token Index: 936

Text #6

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.2154. Min Act: -0.0000

Data Index: 9082 (The Pile)

Max Activating Token Index: 128

Text #7

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.1880. Min Act: -0.0000

Data Index: 1103666 (The Pile)

Max Activating Token Index: 814

Text #8

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.1936. Min Act: -0.0000

Data Index: 930278 (The Pile)

Max Activating Token Index: 49

Text #9

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.1935. Min Act: -0.0000

Data Index: 991919 (The Pile)

Max Activating Token Index: 925

Text #10

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.1798. Min Act: -0.0000

Data Index: 668945 (The Pile)

Max Activating Token Index: 843

Text #11

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1829945 (The Pile)

Max Activating Token Index: 170

Text #12

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.1749. Min Act: -0.0000

Data Index: 891847 (The Pile)

Max Activating Token Index: 692

Text #13

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.1822. Min Act: -0.0000

Data Index: 380157 (The Pile)

Max Activating Token Index: 244

Text #14

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.1811. Min Act: -0.0000

Data Index: 1692103 (The Pile)

Max Activating Token Index: 231

Text #15

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.1750. Min Act: -0.0000

Data Index: 1904655 (The Pile)

Max Activating Token Index: 231

Text #16

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.1767. Min Act: -0.0000

Data Index: 955625 (The Pile)

Max Activating Token Index: 324

Text #17

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.1726. Min Act: -0.0000

Data Index: 526432 (The Pile)

Max Activating Token Index: 877

Text #18

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1605413 (The Pile)

Max Activating Token Index: 145

Text #19

Max Range: 0.2630. Min Range: -0.2630

Max Act: 0.1753. Min Act: -0.0000

Data Index: 1190857 (The Pile)

Max Activating Token Index: 405