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

Dataset: The Pile

Neuron 4653 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.4063. Min Act: -0.0000

Data Index: 1371749 (The Pile)

Max Activating Token Index: 890

Text #1

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2781. Min Act: -0.0000

Data Index: 551701 (The Pile)

Max Activating Token Index: 22

Text #2

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1868301 (The Pile)

Max Activating Token Index: 1020

Text #3

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2569. Min Act: -0.0000

Data Index: 740523 (The Pile)

Max Activating Token Index: 66

Text #4

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2631. Min Act: -0.0000

Data Index: 1370967 (The Pile)

Max Activating Token Index: 795

Text #5

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2356. Min Act: -0.0000

Data Index: 468741 (The Pile)

Max Activating Token Index: 366

Text #6

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2323. Min Act: -0.0000

Data Index: 1213214 (The Pile)

Max Activating Token Index: 187

Text #7

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2386. Min Act: -0.0000

Data Index: 1261405 (The Pile)

Max Activating Token Index: 975

Text #8

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2090. Min Act: -0.0000

Data Index: 266233 (The Pile)

Max Activating Token Index: 813

Text #9

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2137. Min Act: -0.0000

Data Index: 1697086 (The Pile)

Max Activating Token Index: 742

Text #10

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2133. Min Act: -0.0000

Data Index: 672084 (The Pile)

Max Activating Token Index: 547

Text #11

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2253. Min Act: -0.0000

Data Index: 937842 (The Pile)

Max Activating Token Index: 475

Text #12

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2238. Min Act: -0.0000

Data Index: 1938872 (The Pile)

Max Activating Token Index: 417

Text #13

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2111. Min Act: -0.0001

Data Index: 20815 (The Pile)

Max Activating Token Index: 766

Text #14

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1198091 (The Pile)

Max Activating Token Index: 974

Text #15

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.1970. Min Act: -0.0001

Data Index: 1437710 (The Pile)

Max Activating Token Index: 39

Text #16

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2174. Min Act: -0.0001

Data Index: 1973312 (The Pile)

Max Activating Token Index: 721

Text #17

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2025. Min Act: -0.0000

Data Index: 260272 (The Pile)

Max Activating Token Index: 587

Text #18

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2155. Min Act: -0.0000

Data Index: 779417 (The Pile)

Max Activating Token Index: 108

Text #19

Max Range: 0.4063. Min Range: -0.4063

Max Act: 0.2126. Min Act: -0.0000

Data Index: 248060 (The Pile)

Max Activating Token Index: 157