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

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

Neuron 715 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: 0.0989. Min Range: -0.0989

Max Act: 0.0985. Min Act: -0.0002

Data Index: 131799 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0819. Min Act: -0.0002

Data Index: 1115748 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0989. Min Act: -0.0002

Data Index: 717850 (C4 (Web Text))

Max Activating Token Index: 195

Text #3

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0916. Min Act: -0.0002

Data Index: 7795 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1335472 (C4 (Web Text))

Max Activating Token Index: 224

Text #5

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0830. Min Act: -0.0002

Data Index: 894215 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0804. Min Act: -0.0002

Data Index: 379298 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0793. Min Act: -0.0002

Data Index: 370766 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1209807 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0761. Min Act: -0.0002

Data Index: 1054066 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0720. Min Act: -0.0002

Data Index: 1172623 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0741. Min Act: -0.0002

Data Index: 966028 (C4 (Web Text))

Max Activating Token Index: 23

Text #12

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0741. Min Act: -0.0002

Data Index: 1214037 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1149470 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0723. Min Act: -0.0002

Data Index: 247839 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0689. Min Act: -0.0002

Data Index: 201653 (C4 (Web Text))

Max Activating Token Index: 328

Text #16

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0767. Min Act: -0.0002

Data Index: 691332 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0751. Min Act: -0.0002

Data Index: 159594 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0747. Min Act: -0.0002

Data Index: 83478 (C4 (Web Text))

Max Activating Token Index: 18

Text #19

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0712. Min Act: -0.0002

Data Index: 609210 (C4 (Web Text))

Max Activating Token Index: 418