Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3779 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.2339. Min Act: -0.0000

Data Index: 1095008 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.2363. Min Act: -0.0001

Data Index: 496428 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.2076. Min Act: -0.0001

Data Index: 610071 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1942. Min Act: -0.0001

Data Index: 911300 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1843. Min Act: -0.0000

Data Index: 282057 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1868. Min Act: -0.0001

Data Index: 696803 (C4 (Web Text))

Max Activating Token Index: 476

Text #6

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1903. Min Act: -0.0000

Data Index: 1350929 (C4 (Web Text))

Max Activating Token Index: 558

Text #7

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1815. Min Act: -0.0000

Data Index: 1051213 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1809. Min Act: -0.0000

Data Index: 610364 (C4 (Web Text))

Max Activating Token Index: 475

Text #9

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1811. Min Act: -0.0000

Data Index: 28916 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1669. Min Act: -0.0000

Data Index: 239645 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1780. Min Act: -0.0001

Data Index: 1193257 (C4 (Web Text))

Max Activating Token Index: 982

Text #12

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1719. Min Act: -0.0000

Data Index: 546409 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1318335 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1731. Min Act: -0.0001

Data Index: 725333 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1705. Min Act: -0.0000

Data Index: 891743 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1779. Min Act: -0.0001

Data Index: 1257490 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1714. Min Act: -0.0001

Data Index: 17827 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1708. Min Act: -0.0000

Data Index: 307949 (C4 (Web Text))

Max Activating Token Index: 236

Text #19

Max Range: 0.2363. Min Range: -0.2363

Max Act: 0.1738. Min Act: -0.0000

Data Index: 1016274 (C4 (Web Text))

Max Activating Token Index: 885