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

Dataset: The Pile

Neuron 2522 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: 1.0777. Min Range: -1.0777

Max Act: 1.0777. Min Act: -0.0000

Data Index: 1430803 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.2699. Min Act: -0.0000

Data Index: 47159 (The Pile)

Max Activating Token Index: 99

Text #2

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.2650. Min Act: -0.0000

Data Index: 1945524 (The Pile)

Max Activating Token Index: 681

Text #3

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.2319. Min Act: -0.0000

Data Index: 79434 (The Pile)

Max Activating Token Index: 131

Text #4

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.2564. Min Act: -0.0000

Data Index: 563686 (The Pile)

Max Activating Token Index: 195

Text #5

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.2252. Min Act: -0.0000

Data Index: 1861223 (The Pile)

Max Activating Token Index: 930

Text #6

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.1814. Min Act: -0.0000

Data Index: 974218 (The Pile)

Max Activating Token Index: 295

Text #7

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.2469. Min Act: -0.0000

Data Index: 1744953 (The Pile)

Max Activating Token Index: 794

Text #8

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.2365. Min Act: -0.0000

Data Index: 732170 (The Pile)

Max Activating Token Index: 980

Text #9

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1486519 (The Pile)

Max Activating Token Index: 450

Text #10

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.1965. Min Act: -0.0000

Data Index: 1247438 (The Pile)

Max Activating Token Index: 727

Text #11

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.1987. Min Act: -0.0000

Data Index: 1057270 (The Pile)

Max Activating Token Index: 1002

Text #12

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.2043. Min Act: -0.0000

Data Index: 83036 (The Pile)

Max Activating Token Index: 972

Text #13

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.1812. Min Act: -0.0000

Data Index: 88249 (The Pile)

Max Activating Token Index: 416

Text #14

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1848154 (The Pile)

Max Activating Token Index: 24

Text #15

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.1833. Min Act: -0.0000

Data Index: 1150559 (The Pile)

Max Activating Token Index: 891

Text #16

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.2093. Min Act: -0.0000

Data Index: 1968580 (The Pile)

Max Activating Token Index: 100

Text #17

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.1998. Min Act: -0.0000

Data Index: 10815 (The Pile)

Max Activating Token Index: 146

Text #18

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.1851. Min Act: -0.0000

Data Index: 1389061 (The Pile)

Max Activating Token Index: 175

Text #19

Max Range: 1.0777. Min Range: -1.0777

Max Act: 0.1827. Min Act: -0.0000

Data Index: 118944 (The Pile)

Max Activating Token Index: 974