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

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

Neuron 3132 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0881. Min Act: -0.0002

Data Index: 925295 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0788. Min Act: -0.0002

Data Index: 1174534 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0817. Min Act: -0.0001

Data Index: 433101 (C4 (Web Text))

Max Activating Token Index: 4

Text #3

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0771. Min Act: -0.0002

Data Index: 270210 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0790. Min Act: -0.0001

Data Index: 336094 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0798. Min Act: -0.0002

Data Index: 525930 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1205199 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0792. Min Act: -0.0002

Data Index: 297512 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0757. Min Act: -0.0002

Data Index: 601095 (C4 (Web Text))

Max Activating Token Index: 199

Text #9

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0756. Min Act: -0.0001

Data Index: 846489 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0764. Min Act: -0.0001

Data Index: 1103748 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0718. Min Act: -0.0002

Data Index: 635989 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0800. Min Act: -0.0001

Data Index: 187635 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0768. Min Act: -0.0002

Data Index: 1187794 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0795. Min Act: -0.0002

Data Index: 445929 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0733. Min Act: -0.0001

Data Index: 633370 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0764. Min Act: -0.0001

Data Index: 1464036 (Python Code)

Max Activating Token Index: 777

Text #17

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0731. Min Act: -0.0001

Data Index: 1032125 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1238054 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.0881. Min Range: -0.0881

Max Act: 0.0781. Min Act: -0.0001

Data Index: 1176709 (C4 (Web Text))

Max Activating Token Index: 275