Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 598 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0959. Min Act: -0.0003

Data Index: 296664 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0950. Min Act: -0.0004

Data Index: 1207872 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0910. Min Act: -0.0003

Data Index: 375599 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0878. Min Act: -0.0004

Data Index: 501477 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0879. Min Act: -0.0003

Data Index: 872449 (C4 (Web Text))

Max Activating Token Index: 638

Text #5

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0881. Min Act: -0.0003

Data Index: 1065562 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0921. Min Act: -0.0003

Data Index: 593624 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0894. Min Act: -0.0004

Data Index: 1340174 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0858. Min Act: -0.0004

Data Index: 75240 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0871. Min Act: -0.0004

Data Index: 433978 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0867. Min Act: -0.0003

Data Index: 340820 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0892. Min Act: -0.0003

Data Index: 984237 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0873. Min Act: -0.0002

Data Index: 249522 (C4 (Web Text))

Max Activating Token Index: 142

Text #13

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0872. Min Act: -0.0003

Data Index: 1033341 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0847. Min Act: -0.0004

Data Index: 1062121 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0859. Min Act: -0.0003

Data Index: 190373 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0826. Min Act: -0.0003

Data Index: 733715 (C4 (Web Text))

Max Activating Token Index: 499

Text #17

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0838. Min Act: -0.0003

Data Index: 217466 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0838. Min Act: -0.0003

Data Index: 139671 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.0959. Min Range: -0.0959

Max Act: 0.0833. Min Act: -0.0003

Data Index: 200225 (C4 (Web Text))

Max Activating Token Index: 119