Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 22 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1594. Min Act: -0.0000

Data Index: 601130 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1213. Min Act: -0.0000

Data Index: 994872 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1035. Min Act: -0.0000

Data Index: 377434 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1111. Min Act: -0.0000

Data Index: 449928 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.0961. Min Act: -0.0000

Data Index: 405785 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.0992. Min Act: -0.0000

Data Index: 89423 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.0920. Min Act: -0.0000

Data Index: 18944 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.1001. Min Act: -0.0000

Data Index: 1278675 (C4 (Web Text))

Max Activating Token Index: 274

Text #8

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1076901 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.0941. Min Act: -0.0000

Data Index: 609149 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.0847. Min Act: -0.0000

Data Index: 1347849 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.0914. Min Act: -0.0000

Data Index: 521100 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.0870. Min Act: -0.0000

Data Index: 1202954 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.0981. Min Act: -0.0000

Data Index: 165381 (C4 (Web Text))

Max Activating Token Index: 344

Text #14

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.0886. Min Act: -0.0000

Data Index: 639012 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.0781. Min Act: -0.0000

Data Index: 401241 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.0864. Min Act: -0.0000

Data Index: 914353 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.0812. Min Act: -0.0000

Data Index: 270047 (C4 (Web Text))

Max Activating Token Index: 56

Text #18

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.0828. Min Act: -0.0000

Data Index: 595291 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 0.1594. Min Range: -0.1594

Max Act: 0.0797. Min Act: -0.0000

Data Index: 822723 (C4 (Web Text))

Max Activating Token Index: 251