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

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

Neuron 4775 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.1166. Min Act: -0.0002

Data Index: 1217342 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1214143 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0957. Min Act: -0.0002

Data Index: 329208 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.1005. Min Act: -0.0002

Data Index: 509224 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.1010. Min Act: -0.0002

Data Index: 1354944 (C4 (Web Text))

Max Activating Token Index: 21

Text #5

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0966. Min Act: -0.0002

Data Index: 1175437 (C4 (Web Text))

Max Activating Token Index: 874

Text #6

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0923. Min Act: -0.0002

Data Index: 329971 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0949. Min Act: -0.0002

Data Index: 1093303 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0935. Min Act: -0.0002

Data Index: 972544 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0941. Min Act: -0.0002

Data Index: 25213 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0950. Min Act: -0.0002

Data Index: 497237 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0903. Min Act: -0.0002

Data Index: 696711 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0901. Min Act: -0.0002

Data Index: 1231573 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0902. Min Act: -0.0002

Data Index: 266848 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0927. Min Act: -0.0002

Data Index: 489773 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0920. Min Act: -0.0002

Data Index: 373737 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0864. Min Act: -0.0002

Data Index: 1267255 (C4 (Web Text))

Max Activating Token Index: 821

Text #17

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0884. Min Act: -0.0002

Data Index: 764621 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0914. Min Act: -0.0002

Data Index: 417971 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.1166. Min Range: -0.1166

Max Act: 0.0890. Min Act: -0.0002

Data Index: 217080 (C4 (Web Text))

Max Activating Token Index: 134