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

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

Neuron 1132 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8389. Min Range: -3.8389

Max Act: 3.8389. Min Act: -0.0000

Data Index: 868140 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 3.8389. Min Range: -3.8389

Max Act: 3.1138. Min Act: -0.0000

Data Index: 180059 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 3.8389. Min Range: -3.8389

Max Act: 2.9753. Min Act: -0.0000

Data Index: 317002 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 3.8389. Min Range: -3.8389

Max Act: 3.0458. Min Act: -0.0000

Data Index: 313612 (C4 (Web Text))

Max Activating Token Index: 389

Text #4

Max Range: 3.8389. Min Range: -3.8389

Max Act: 2.9471. Min Act: -0.0000

Data Index: 1048864 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 3.8389. Min Range: -3.8389

Max Act: 2.9585. Min Act: -0.0000

Data Index: 1311128 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 3.8389. Min Range: -3.8389

Max Act: 2.7634. Min Act: -0.0000

Data Index: 896653 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 3.8389. Min Range: -3.8389

Max Act: 2.4723. Min Act: -0.0000

Data Index: 5479 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 3.8389. Min Range: -3.8389

Max Act: 2.7374. Min Act: -0.0000

Data Index: 859231 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 3.8389. Min Range: -3.8389

Max Act: 2.4999. Min Act: -0.0000

Data Index: 584171 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 3.8389. Min Range: -3.8389

Max Act: 2.5043. Min Act: -0.0000

Data Index: 325772 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 3.8389. Min Range: -3.8389

Max Act: 2.2493. Min Act: -0.0000

Data Index: 222868 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 3.8389. Min Range: -3.8389

Max Act: 2.3546. Min Act: -0.0000

Data Index: 663950 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 3.8389. Min Range: -3.8389

Max Act: 2.2263. Min Act: -0.0000

Data Index: 581767 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 3.8389. Min Range: -3.8389

Max Act: 2.3064. Min Act: -0.0000

Data Index: 413171 (C4 (Web Text))

Max Activating Token Index: 641

Text #15

Max Range: 3.8389. Min Range: -3.8389

Max Act: 2.2816. Min Act: -0.0000

Data Index: 688923 (C4 (Web Text))

Max Activating Token Index: 648

Text #16

Max Range: 3.8389. Min Range: -3.8389

Max Act: 2.0528. Min Act: -0.0000

Data Index: 936754 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 3.8389. Min Range: -3.8389

Max Act: 2.1495. Min Act: -0.0000

Data Index: 940193 (C4 (Web Text))

Max Activating Token Index: 138

Text #18

Max Range: 3.8389. Min Range: -3.8389

Max Act: 2.0261. Min Act: 0.0000

Data Index: 1159839 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 3.8389. Min Range: -3.8389

Max Act: 2.0118. Min Act: -0.0000

Data Index: 1255437 (C4 (Web Text))

Max Activating Token Index: 710