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

Dataset: The Pile

Neuron 824 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: 0.2482. Min Range: -0.2482

Max Act: 0.2482. Min Act: -0.0000

Data Index: 97859 (The Pile)

Max Activating Token Index: 584

Text #1

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2469. Min Act: -0.0000

Data Index: 542040 (The Pile)

Max Activating Token Index: 190

Text #2

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1117333 (The Pile)

Max Activating Token Index: 816

Text #3

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2140. Min Act: -0.0000

Data Index: 441828 (The Pile)

Max Activating Token Index: 687

Text #4

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1130520 (The Pile)

Max Activating Token Index: 779

Text #5

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1923. Min Act: -0.0000

Data Index: 59113 (The Pile)

Max Activating Token Index: 593

Text #6

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1837. Min Act: -0.0000

Data Index: 935617 (The Pile)

Max Activating Token Index: 161

Text #7

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2142. Min Act: -0.0000

Data Index: 836208 (The Pile)

Max Activating Token Index: 104

Text #8

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1927. Min Act: -0.0000

Data Index: 1326144 (The Pile)

Max Activating Token Index: 484

Text #9

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.2104. Min Act: -0.0000

Data Index: 1204725 (The Pile)

Max Activating Token Index: 514

Text #10

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1910. Min Act: -0.0000

Data Index: 328787 (The Pile)

Max Activating Token Index: 151

Text #11

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1884. Min Act: -0.0000

Data Index: 87090 (The Pile)

Max Activating Token Index: 999

Text #12

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1810. Min Act: -0.0000

Data Index: 1179356 (The Pile)

Max Activating Token Index: 484

Text #13

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1998. Min Act: -0.0000

Data Index: 1975695 (The Pile)

Max Activating Token Index: 706

Text #14

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1961. Min Act: -0.0000

Data Index: 459579 (The Pile)

Max Activating Token Index: 222

Text #15

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1960. Min Act: -0.0000

Data Index: 1221613 (The Pile)

Max Activating Token Index: 301

Text #16

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1728074 (The Pile)

Max Activating Token Index: 344

Text #17

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1719. Min Act: -0.0000

Data Index: 1934735 (The Pile)

Max Activating Token Index: 893

Text #18

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1732. Min Act: -0.0000

Data Index: 1932562 (The Pile)

Max Activating Token Index: 922

Text #19

Max Range: 0.2482. Min Range: -0.2482

Max Act: 0.1853. Min Act: -0.0000

Data Index: 1632947 (The Pile)

Max Activating Token Index: 304