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

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

Neuron 708 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0911. Min Act: -0.0002

Data Index: 300219 (C4 (Web Text))

Max Activating Token Index: 298

Text #1

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0780. Min Act: -0.0002

Data Index: 430473 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0694. Min Act: -0.0002

Data Index: 362237 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0833. Min Act: -0.0002

Data Index: 559360 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1259905 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0885. Min Act: -0.0002

Data Index: 434449 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0793. Min Act: -0.0002

Data Index: 218862 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0702. Min Act: -0.0002

Data Index: 476246 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0772. Min Act: -0.0002

Data Index: 1313049 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0805. Min Act: -0.0002

Data Index: 687774 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0707. Min Act: -0.0002

Data Index: 131692 (C4 (Web Text))

Max Activating Token Index: 322

Text #11

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0779. Min Act: -0.0002

Data Index: 251538 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0713. Min Act: -0.0002

Data Index: 305704 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0788. Min Act: -0.0002

Data Index: 997020 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0669. Min Act: -0.0002

Data Index: 913259 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1192359 (C4 (Web Text))

Max Activating Token Index: 815

Text #16

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0719. Min Act: -0.0002

Data Index: 1071879 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0710. Min Act: -0.0002

Data Index: 1347238 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0923. Min Act: -0.0002

Data Index: 796727 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 0.0923. Min Range: -0.0923

Max Act: 0.0686. Min Act: -0.0002

Data Index: 984732 (C4 (Web Text))

Max Activating Token Index: 388