Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1589 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1115. Min Act: -0.0001

Data Index: 783913 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1138. Min Act: -0.0001

Data Index: 706994 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1044. Min Act: -0.0001

Data Index: 121294 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1053. Min Act: -0.0001

Data Index: 1116679 (C4 (Web Text))

Max Activating Token Index: 1021

Text #4

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0830. Min Act: -0.0001

Data Index: 784527 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0931. Min Act: -0.0001

Data Index: 408605 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0831. Min Act: -0.0001

Data Index: 632705 (C4 (Web Text))

Max Activating Token Index: 840

Text #7

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0928. Min Act: -0.0001

Data Index: 1245495 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0955. Min Act: -0.0001

Data Index: 632728 (C4 (Web Text))

Max Activating Token Index: 540

Text #9

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0922. Min Act: -0.0001

Data Index: 751472 (C4 (Web Text))

Max Activating Token Index: 973

Text #10

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0859. Min Act: -0.0001

Data Index: 223837 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0916. Min Act: -0.0001

Data Index: 130138 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0914. Min Act: -0.0001

Data Index: 571753 (C4 (Web Text))

Max Activating Token Index: 274

Text #13

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0939. Min Act: -0.0001

Data Index: 523271 (C4 (Web Text))

Max Activating Token Index: 548

Text #14

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0905. Min Act: -0.0001

Data Index: 631364 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0865. Min Act: -0.0001

Data Index: 1033866 (C4 (Web Text))

Max Activating Token Index: 394

Text #16

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0864. Min Act: -0.0001

Data Index: 950734 (C4 (Web Text))

Max Activating Token Index: 379

Text #17

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0856. Min Act: -0.0001

Data Index: 648818 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0852. Min Act: -0.0001

Data Index: 137059 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0841. Min Act: -0.0001

Data Index: 574788 (C4 (Web Text))

Max Activating Token Index: 350