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

Dataset: The Pile

Neuron 3184 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: 0.3155. Min Range: -0.3155

Max Act: 0.3155. Min Act: -0.0000

Data Index: 1784740 (The Pile)

Max Activating Token Index: 757

Text #1

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2316. Min Act: -0.0000

Data Index: 559056 (The Pile)

Max Activating Token Index: 514

Text #2

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2300. Min Act: -0.0000

Data Index: 843925 (The Pile)

Max Activating Token Index: 992

Text #3

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1025666 (The Pile)

Max Activating Token Index: 158

Text #4

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2256. Min Act: -0.0000

Data Index: 673972 (The Pile)

Max Activating Token Index: 725

Text #5

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2074. Min Act: -0.0000

Data Index: 456681 (The Pile)

Max Activating Token Index: 689

Text #6

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.1987. Min Act: -0.0000

Data Index: 905198 (The Pile)

Max Activating Token Index: 662

Text #7

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2132. Min Act: -0.0000

Data Index: 472260 (The Pile)

Max Activating Token Index: 165

Text #8

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.1956. Min Act: -0.0000

Data Index: 80352 (The Pile)

Max Activating Token Index: 748

Text #9

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.1957. Min Act: -0.0000

Data Index: 1422501 (The Pile)

Max Activating Token Index: 825

Text #10

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.1967. Min Act: -0.0000

Data Index: 1299751 (The Pile)

Max Activating Token Index: 168

Text #11

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1318886 (The Pile)

Max Activating Token Index: 1009

Text #12

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.1991. Min Act: -0.0000

Data Index: 1839314 (The Pile)

Max Activating Token Index: 198

Text #13

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2003. Min Act: -0.0000

Data Index: 91123 (The Pile)

Max Activating Token Index: 265

Text #14

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.1915. Min Act: -0.0000

Data Index: 1377242 (The Pile)

Max Activating Token Index: 906

Text #15

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1150805 (The Pile)

Max Activating Token Index: 595

Text #16

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2097. Min Act: -0.0000

Data Index: 918529 (The Pile)

Max Activating Token Index: 806

Text #17

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.2159. Min Act: -0.0000

Data Index: 846789 (The Pile)

Max Activating Token Index: 839

Text #18

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.1965. Min Act: -0.0000

Data Index: 1062061 (The Pile)

Max Activating Token Index: 655

Text #19

Max Range: 0.3155. Min Range: -0.3155

Max Act: 0.1889. Min Act: -0.0000

Data Index: 438773 (The Pile)

Max Activating Token Index: 292