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

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

Neuron 1292 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: 0.0981. Min Range: -0.0981

Max Act: 0.0981. Min Act: -0.0003

Data Index: 131279 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0909. Min Act: -0.0003

Data Index: 271387 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0850. Min Act: -0.0003

Data Index: 245506 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0870. Min Act: -0.0003

Data Index: 1166917 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0873. Min Act: -0.0003

Data Index: 1067542 (C4 (Web Text))

Max Activating Token Index: 856

Text #5

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0882. Min Act: -0.0003

Data Index: 866579 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0864. Min Act: -0.0003

Data Index: 1157414 (C4 (Web Text))

Max Activating Token Index: 511

Text #7

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0859. Min Act: -0.0003

Data Index: 801973 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0846. Min Act: -0.0003

Data Index: 102114 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0839. Min Act: -0.0003

Data Index: 75725 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0843. Min Act: -0.0003

Data Index: 248619 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0829. Min Act: -0.0004

Data Index: 969637 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0826. Min Act: -0.0004

Data Index: 576201 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0830. Min Act: -0.0003

Data Index: 509394 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0815. Min Act: -0.0003

Data Index: 215986 (C4 (Web Text))

Max Activating Token Index: 237

Text #15

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0829. Min Act: -0.0003

Data Index: 653853 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0813. Min Act: -0.0003

Data Index: 747588 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0818. Min Act: -0.0003

Data Index: 41059 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0820. Min Act: -0.0003

Data Index: 1292987 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 0.0981. Min Range: -0.0981

Max Act: 0.0823. Min Act: -0.0003

Data Index: 654336 (C4 (Web Text))

Max Activating Token Index: 27