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

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

Neuron 2214 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1191. Min Act: -0.0000

Data Index: 673081 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1350. Min Act: -0.0000

Data Index: 94286 (C4 (Web Text))

Max Activating Token Index: 958

Text #2

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1200. Min Act: -0.0000

Data Index: 1024130 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1197. Min Act: -0.0000

Data Index: 280176 (C4 (Web Text))

Max Activating Token Index: 890

Text #4

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1177. Min Act: -0.0000

Data Index: 1314896 (C4 (Web Text))

Max Activating Token Index: 162

Text #5

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1139. Min Act: -0.0000

Data Index: 143716 (C4 (Web Text))

Max Activating Token Index: 429

Text #6

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1247. Min Act: -0.0000

Data Index: 728445 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1146. Min Act: -0.0000

Data Index: 654825 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1136. Min Act: -0.0000

Data Index: 873232 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1093. Min Act: -0.0000

Data Index: 426710 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1110. Min Act: -0.0000

Data Index: 272514 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1021. Min Act: -0.0000

Data Index: 1019050 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1112. Min Act: -0.0000

Data Index: 519958 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1062. Min Act: -0.0000

Data Index: 396895 (C4 (Web Text))

Max Activating Token Index: 369

Text #14

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0969. Min Act: -0.0000

Data Index: 80352 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0930. Min Act: -0.0000

Data Index: 410226 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0992. Min Act: -0.0000

Data Index: 779798 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1000114 (C4 (Web Text))

Max Activating Token Index: 193

Text #18

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0978. Min Act: -0.0000

Data Index: 26377 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 0.1350. Min Range: -0.1350

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1065153 (C4 (Web Text))

Max Activating Token Index: 115