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

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

Neuron 108 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.1092. Min Act: -0.0003

Data Index: 1351127 (C4 (Web Text))

Max Activating Token Index: 284

Text #1

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.1055. Min Act: -0.0003

Data Index: 1283695 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0999. Min Act: -0.0003

Data Index: 1333929 (C4 (Web Text))

Max Activating Token Index: 1022

Text #3

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0960. Min Act: -0.0003

Data Index: 1106412 (C4 (Web Text))

Max Activating Token Index: 582

Text #4

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0910. Min Act: -0.0003

Data Index: 717046 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0944. Min Act: -0.0003

Data Index: 250826 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0896. Min Act: -0.0003

Data Index: 1015845 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0917. Min Act: -0.0003

Data Index: 1237107 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0948. Min Act: -0.0003

Data Index: 37698 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0883. Min Act: -0.0003

Data Index: 860966 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0942. Min Act: -0.0003

Data Index: 1329829 (C4 (Web Text))

Max Activating Token Index: 908

Text #11

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0943. Min Act: -0.0003

Data Index: 866668 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0954. Min Act: -0.0003

Data Index: 130279 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0920. Min Act: -0.0003

Data Index: 1206444 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0878. Min Act: -0.0003

Data Index: 542566 (C4 (Web Text))

Max Activating Token Index: 1014

Text #15

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0919. Min Act: -0.0003

Data Index: 178268 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0951. Min Act: -0.0003

Data Index: 193316 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0875. Min Act: -0.0003

Data Index: 139366 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0943. Min Act: -0.0003

Data Index: 996853 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0898. Min Act: -0.0003

Data Index: 429508 (C4 (Web Text))

Max Activating Token Index: 451