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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3110 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1116. Min Act: -0.0001

Data Index: 776889 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1244. Min Act: -0.0000

Data Index: 508115 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1162. Min Act: -0.0000

Data Index: 211236 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1225. Min Act: -0.0001

Data Index: 1048642 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1102. Min Act: -0.0000

Data Index: 822255 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1101. Min Act: -0.0000

Data Index: 1330761 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1089. Min Act: -0.0000

Data Index: 17206 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1019. Min Act: -0.0000

Data Index: 1241845 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0999. Min Act: -0.0000

Data Index: 127519 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1056. Min Act: -0.0000

Data Index: 1050641 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1045. Min Act: -0.0000

Data Index: 126354 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0992. Min Act: -0.0000

Data Index: 788447 (C4 (Web Text))

Max Activating Token Index: 11

Text #12

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0946. Min Act: -0.0000

Data Index: 1267883 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1018. Min Act: -0.0000

Data Index: 490614 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0966. Min Act: -0.0000

Data Index: 1324050 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0942. Min Act: -0.0000

Data Index: 636346 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.1033. Min Act: -0.0000

Data Index: 53084 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0990. Min Act: -0.0000

Data Index: 854822 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0919. Min Act: -0.0001

Data Index: 381682 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 0.1244. Min Range: -0.1244

Max Act: 0.0817. Min Act: -0.0000

Data Index: 416324 (C4 (Web Text))

Max Activating Token Index: 176