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

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

Neuron 4585 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0982. Min Act: -0.0002

Data Index: 791419 (C4 (Web Text))

Max Activating Token Index: 366

Text #1

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0896. Min Act: -0.0002

Data Index: 966937 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0842. Min Act: -0.0002

Data Index: 234884 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0826. Min Act: -0.0002

Data Index: 297909 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0821. Min Act: -0.0002

Data Index: 905271 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0783. Min Act: -0.0002

Data Index: 361425 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0767. Min Act: -0.0002

Data Index: 228907 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0735. Min Act: -0.0002

Data Index: 795984 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1166671 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0737. Min Act: -0.0002

Data Index: 833571 (C4 (Web Text))

Max Activating Token Index: 463

Text #10

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0694. Min Act: -0.0002

Data Index: 276590 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0720. Min Act: -0.0002

Data Index: 374874 (C4 (Web Text))

Max Activating Token Index: 756

Text #12

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0719. Min Act: -0.0002

Data Index: 168111 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0663. Min Act: -0.0002

Data Index: 152795 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0689. Min Act: -0.0002

Data Index: 810356 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0710. Min Act: -0.0002

Data Index: 142567 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0663. Min Act: -0.0002

Data Index: 115775 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0660. Min Act: -0.0002

Data Index: 224269 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0627. Min Act: -0.0002

Data Index: 980184 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0651. Min Act: -0.0002

Data Index: 926965 (C4 (Web Text))

Max Activating Token Index: 478