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

Dataset: The Pile

Neuron 2172 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 5.0022. Min Range: -5.0022

Max Act: 5.0022. Min Act: -0.0000

Data Index: 121155 (The Pile)

Max Activating Token Index: 20

Text #1

Max Range: 5.0022. Min Range: -5.0022

Max Act: 4.3570. Min Act: -0.0000

Data Index: 577019 (The Pile)

Max Activating Token Index: 31

Text #2

Max Range: 5.0022. Min Range: -5.0022

Max Act: 4.4776. Min Act: -0.0000

Data Index: 932092 (The Pile)

Max Activating Token Index: 120

Text #3

Max Range: 5.0022. Min Range: -5.0022

Max Act: 4.5013. Min Act: -0.0000

Data Index: 421859 (The Pile)

Max Activating Token Index: 9

Text #4

Max Range: 5.0022. Min Range: -5.0022

Max Act: 4.2927. Min Act: -0.0000

Data Index: 1693252 (The Pile)

Max Activating Token Index: 19

Text #5

Max Range: 5.0022. Min Range: -5.0022

Max Act: 4.2672. Min Act: -0.0000

Data Index: 1951444 (The Pile)

Max Activating Token Index: 14

Text #6

Max Range: 5.0022. Min Range: -5.0022

Max Act: 4.4105. Min Act: -0.0000

Data Index: 911354 (The Pile)

Max Activating Token Index: 38

Text #7

Max Range: 5.0022. Min Range: -5.0022

Max Act: 4.2172. Min Act: -0.0000

Data Index: 419051 (The Pile)

Max Activating Token Index: 10

Text #8

Max Range: 5.0022. Min Range: -5.0022

Max Act: 4.1939. Min Act: -0.0000

Data Index: 21185 (The Pile)

Max Activating Token Index: 78

Text #9

Max Range: 5.0022. Min Range: -5.0022

Max Act: 4.3312. Min Act: -0.0000

Data Index: 1028739 (The Pile)

Max Activating Token Index: 88

Text #10

Max Range: 5.0022. Min Range: -5.0022

Max Act: 4.3116. Min Act: -0.0000

Data Index: 1840164 (The Pile)

Max Activating Token Index: 186

Text #11

Max Range: 5.0022. Min Range: -5.0022

Max Act: 4.3114. Min Act: -0.0000

Data Index: 1189609 (The Pile)

Max Activating Token Index: 971

Text #12

Max Range: 5.0022. Min Range: -5.0022

Max Act: 4.2786. Min Act: -0.0000

Data Index: 566949 (The Pile)

Max Activating Token Index: 1015

Text #13

Max Range: 5.0022. Min Range: -5.0022

Max Act: 4.1358. Min Act: -0.0000

Data Index: 908013 (The Pile)

Max Activating Token Index: 144

Text #14

Max Range: 5.0022. Min Range: -5.0022

Max Act: 4.2668. Min Act: -0.0000

Data Index: 280580 (The Pile)

Max Activating Token Index: 374

Text #15

Max Range: 5.0022. Min Range: -5.0022

Max Act: 4.0592. Min Act: -0.0000

Data Index: 1829399 (The Pile)

Max Activating Token Index: 902

Text #16

Max Range: 5.0022. Min Range: -5.0022

Max Act: 4.0526. Min Act: -0.0000

Data Index: 1897015 (The Pile)

Max Activating Token Index: 144

Text #17

Max Range: 5.0022. Min Range: -5.0022

Max Act: 4.1996. Min Act: -0.0000

Data Index: 1521893 (The Pile)

Max Activating Token Index: 182

Text #18

Max Range: 5.0022. Min Range: -5.0022

Max Act: 4.2368. Min Act: -0.0000

Data Index: 1473897 (The Pile)

Max Activating Token Index: 172

Text #19

Max Range: 5.0022. Min Range: -5.0022

Max Act: 4.2229. Min Act: -0.0000

Data Index: 407760 (The Pile)

Max Activating Token Index: 341