Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 683 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0878. Min Act: -0.0001

Data Index: 691434 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0820. Min Act: -0.0001

Data Index: 510769 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0884. Min Act: -0.0002

Data Index: 71652 (C4 (Web Text))

Max Activating Token Index: 919

Text #3

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0698. Min Act: -0.0002

Data Index: 283047 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0797. Min Act: -0.0002

Data Index: 1335975 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1291882 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0778. Min Act: -0.0002

Data Index: 931013 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0766. Min Act: -0.0002

Data Index: 892765 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0753. Min Act: -0.0002

Data Index: 526230 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0754. Min Act: -0.0002

Data Index: 125536 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0751. Min Act: -0.0002

Data Index: 124913 (C4 (Web Text))

Max Activating Token Index: 693

Text #11

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0696. Min Act: -0.0002

Data Index: 682961 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0713. Min Act: -0.0002

Data Index: 861226 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0739. Min Act: -0.0002

Data Index: 571921 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0740. Min Act: -0.0002

Data Index: 760802 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0736. Min Act: -0.0001

Data Index: 1252384 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0709. Min Act: -0.0002

Data Index: 319842 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0722. Min Act: -0.0002

Data Index: 1313273 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1116822 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.0884. Min Range: -0.0884

Max Act: 0.0731. Min Act: -0.0002

Data Index: 668900 (C4 (Web Text))

Max Activating Token Index: 254