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

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

Neuron 532 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: 0.0910. Min Range: -0.0910

Max Act: 0.0910. Min Act: -0.0001

Data Index: 922063 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1235420 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0827. Min Act: -0.0001

Data Index: 531970 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0830. Min Act: -0.0001

Data Index: 345192 (C4 (Web Text))

Max Activating Token Index: 903

Text #4

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0774. Min Act: -0.0001

Data Index: 1315438 (C4 (Web Text))

Max Activating Token Index: 419

Text #5

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0734. Min Act: -0.0001

Data Index: 1319299 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0789. Min Act: -0.0002

Data Index: 54365 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0760. Min Act: -0.0001

Data Index: 948754 (C4 (Web Text))

Max Activating Token Index: 493

Text #8

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0718. Min Act: -0.0001

Data Index: 1211705 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0793. Min Act: -0.0002

Data Index: 958164 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0731. Min Act: -0.0002

Data Index: 240196 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0764. Min Act: -0.0001

Data Index: 959240 (C4 (Web Text))

Max Activating Token Index: 416

Text #12

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0674. Min Act: -0.0001

Data Index: 577846 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0700. Min Act: -0.0001

Data Index: 1123505 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1007946 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0684. Min Act: -0.0002

Data Index: 384193 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0724. Min Act: -0.0001

Data Index: 479696 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0699. Min Act: -0.0001

Data Index: 1290830 (C4 (Web Text))

Max Activating Token Index: 891

Text #18

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0674. Min Act: -0.0002

Data Index: 848187 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0691. Min Act: -0.0002

Data Index: 1131169 (C4 (Web Text))

Max Activating Token Index: 240