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

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

Neuron 769 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0966. Min Act: -0.0002

Data Index: 625014 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0958. Min Act: -0.0002

Data Index: 767314 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0933. Min Act: -0.0002

Data Index: 644198 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0911. Min Act: -0.0002

Data Index: 638483 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0910. Min Act: -0.0002

Data Index: 894825 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0906. Min Act: -0.0002

Data Index: 1149253 (C4 (Web Text))

Max Activating Token Index: 62

Text #6

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0909. Min Act: -0.0002

Data Index: 1073060 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0900. Min Act: -0.0002

Data Index: 294082 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0899. Min Act: -0.0002

Data Index: 23863 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0897. Min Act: -0.0002

Data Index: 1120032 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0864. Min Act: -0.0002

Data Index: 197141 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0891. Min Act: -0.0002

Data Index: 1087986 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1096131 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0889. Min Act: -0.0002

Data Index: 291538 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0887. Min Act: -0.0002

Data Index: 237092 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0892. Min Act: -0.0002

Data Index: 658137 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0887. Min Act: -0.0002

Data Index: 823743 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0885. Min Act: -0.0002

Data Index: 1320655 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0884. Min Act: -0.0002

Data Index: 1201766 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 0.0966. Min Range: -0.0966

Max Act: 0.0851. Min Act: -0.0002

Data Index: 379150 (C4 (Web Text))

Max Activating Token Index: 50