Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3400 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1626. Min Act: -0.0000

Data Index: 1031224 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1404. Min Act: -0.0000

Data Index: 229809 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1298. Min Act: -0.0000

Data Index: 127313 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1246. Min Act: -0.0000

Data Index: 68157 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1143. Min Act: -0.0000

Data Index: 1143796 (C4 (Web Text))

Max Activating Token Index: 367

Text #5

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1247. Min Act: -0.0000

Data Index: 458192 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1153. Min Act: -0.0000

Data Index: 917740 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1248. Min Act: -0.0000

Data Index: 18459 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1347. Min Act: -0.0000

Data Index: 859308 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1144. Min Act: -0.0000

Data Index: 1077789 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1114. Min Act: -0.0000

Data Index: 230333 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1125285 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.0984. Min Act: -0.0001

Data Index: 1086961 (C4 (Web Text))

Max Activating Token Index: 808

Text #13

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1197. Min Act: -0.0000

Data Index: 1249979 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1101. Min Act: -0.0001

Data Index: 452640 (C4 (Web Text))

Max Activating Token Index: 85

Text #15

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.0892. Min Act: -0.0001

Data Index: 600371 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1105. Min Act: -0.0001

Data Index: 1303925 (C4 (Web Text))

Max Activating Token Index: 162

Text #17

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1118. Min Act: -0.0000

Data Index: 725037 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1070. Min Act: -0.0000

Data Index: 355197 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 0.1626. Min Range: -0.1626

Max Act: 0.1105. Min Act: -0.0001

Data Index: 57936 (C4 (Web Text))

Max Activating Token Index: 684