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

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

Neuron 2077 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: 0.1068. Min Range: -0.1068

Max Act: 0.1024. Min Act: -0.0002

Data Index: 323861 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.1068. Min Act: -0.0002

Data Index: 346977 (C4 (Web Text))

Max Activating Token Index: 243

Text #2

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0930. Min Act: -0.0002

Data Index: 788748 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.1025. Min Act: -0.0002

Data Index: 1259246 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0966. Min Act: -0.0002

Data Index: 1319875 (C4 (Web Text))

Max Activating Token Index: 915

Text #5

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0958. Min Act: -0.0002

Data Index: 1092675 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0926. Min Act: -0.0002

Data Index: 492218 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0977. Min Act: -0.0002

Data Index: 1021260 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0941. Min Act: -0.0002

Data Index: 335803 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0962. Min Act: -0.0002

Data Index: 36988 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0932. Min Act: -0.0002

Data Index: 1055509 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0919. Min Act: -0.0002

Data Index: 975229 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0978. Min Act: -0.0002

Data Index: 943189 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0964. Min Act: -0.0002

Data Index: 189217 (C4 (Web Text))

Max Activating Token Index: 312

Text #14

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0928. Min Act: -0.0002

Data Index: 502564 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0898. Min Act: -0.0002

Data Index: 403083 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0867. Min Act: -0.0002

Data Index: 1035731 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0919. Min Act: -0.0002

Data Index: 1200031 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0931. Min Act: -0.0002

Data Index: 370684 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 0.1068. Min Range: -0.1068

Max Act: 0.0825. Min Act: -0.0002

Data Index: 1164856 (C4 (Web Text))

Max Activating Token Index: 250