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

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

Neuron 2050 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.1165. Min Act: -0.0000

Data Index: 1152942 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0989. Min Act: -0.0001

Data Index: 204400 (C4 (Web Text))

Max Activating Token Index: 463

Text #2

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0843. Min Act: -0.0000

Data Index: 101418 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0928. Min Act: -0.0001

Data Index: 856550 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0931. Min Act: -0.0001

Data Index: 150551 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0913. Min Act: -0.0001

Data Index: 1288454 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0941. Min Act: -0.0001

Data Index: 1588934 (Python Code)

Max Activating Token Index: 313

Text #7

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0886. Min Act: -0.0001

Data Index: 1383963 (Python Code)

Max Activating Token Index: 995

Text #8

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0855. Min Act: -0.0001

Data Index: 1538764 (Python Code)

Max Activating Token Index: 758

Text #9

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0856. Min Act: -0.0000

Data Index: 1179244 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0868. Min Act: -0.0001

Data Index: 1636761 (Python Code)

Max Activating Token Index: 570

Text #11

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0811. Min Act: -0.0001

Data Index: 1101068 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0820. Min Act: -0.0001

Data Index: 59302 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0811. Min Act: -0.0001

Data Index: 1555445 (Python Code)

Max Activating Token Index: 495

Text #14

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0836. Min Act: -0.0001

Data Index: 485237 (C4 (Web Text))

Max Activating Token Index: 43

Text #15

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0803. Min Act: -0.0000

Data Index: 769821 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0799. Min Act: -0.0001

Data Index: 1505786 (Python Code)

Max Activating Token Index: 378

Text #17

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0756. Min Act: -0.0000

Data Index: 696622 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0821. Min Act: -0.0001

Data Index: 59718 (C4 (Web Text))

Max Activating Token Index: 35

Text #19

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0787. Min Act: -0.0001

Data Index: 775962 (C4 (Web Text))

Max Activating Token Index: 16