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

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

Neuron 3541 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1669. Min Act: -0.0000

Data Index: 85827 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1256. Min Act: -0.0000

Data Index: 1611633 (Python Code)

Max Activating Token Index: 220

Text #2

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1118. Min Act: -0.0001

Data Index: 1598270 (Python Code)

Max Activating Token Index: 678

Text #3

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1294. Min Act: -0.0001

Data Index: 1502356 (Python Code)

Max Activating Token Index: 157

Text #4

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1227. Min Act: -0.0000

Data Index: 1536244 (Python Code)

Max Activating Token Index: 704

Text #5

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1161. Min Act: -0.0000

Data Index: 1086443 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1079. Min Act: -0.0001

Data Index: 1600223 (Python Code)

Max Activating Token Index: 503

Text #7

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1109. Min Act: -0.0000

Data Index: 1208618 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1072. Min Act: -0.0000

Data Index: 483308 (C4 (Web Text))

Max Activating Token Index: 251

Text #9

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1060. Min Act: -0.0001

Data Index: 1625455 (Python Code)

Max Activating Token Index: 27

Text #10

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1054. Min Act: -0.0000

Data Index: 673248 (C4 (Web Text))

Max Activating Token Index: 318

Text #11

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1009. Min Act: -0.0001

Data Index: 1383113 (Python Code)

Max Activating Token Index: 505

Text #12

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1034. Min Act: -0.0000

Data Index: 314044 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1019. Min Act: -0.0000

Data Index: 1029519 (C4 (Web Text))

Max Activating Token Index: 20

Text #14

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1071. Min Act: -0.0001

Data Index: 1575283 (Python Code)

Max Activating Token Index: 246

Text #15

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1061. Min Act: -0.0000

Data Index: 162882 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1015. Min Act: -0.0000

Data Index: 548311 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1037. Min Act: -0.0000

Data Index: 944347 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.0971. Min Act: -0.0001

Data Index: 1523962 (Python Code)

Max Activating Token Index: 863

Text #19

Max Range: 0.1669. Min Range: -0.1669

Max Act: 0.1007. Min Act: -0.0000

Data Index: 764850 (C4 (Web Text))

Max Activating Token Index: 565