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

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

Neuron 1558 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.4917. Min Range: -7.4917

Max Act: 7.4917. Min Act: -0.0001

Data Index: 175516 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 7.4917. Min Range: -7.4917

Max Act: 7.1630. Min Act: -0.0001

Data Index: 180773 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 7.4917. Min Range: -7.4917

Max Act: 5.5135. Min Act: -0.0001

Data Index: 913380 (C4 (Web Text))

Max Activating Token Index: 550

Text #3

Max Range: 7.4917. Min Range: -7.4917

Max Act: 3.7515. Min Act: -0.0001

Data Index: 157336 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 7.4917. Min Range: -7.4917

Max Act: 4.1659. Min Act: -0.0001

Data Index: 319054 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 7.4917. Min Range: -7.4917

Max Act: 3.9963. Min Act: -0.0000

Data Index: 1067091 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 7.4917. Min Range: -7.4917

Max Act: 3.9815. Min Act: -0.0001

Data Index: 1200756 (C4 (Web Text))

Max Activating Token Index: 451

Text #7

Max Range: 7.4917. Min Range: -7.4917

Max Act: 3.6554. Min Act: -0.0001

Data Index: 465592 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 7.4917. Min Range: -7.4917

Max Act: 3.3272. Min Act: -0.0001

Data Index: 1271136 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 7.4917. Min Range: -7.4917

Max Act: 3.5659. Min Act: -0.0001

Data Index: 538610 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 7.4917. Min Range: -7.4917

Max Act: 3.2684. Min Act: -0.0000

Data Index: 779789 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 7.4917. Min Range: -7.4917

Max Act: 3.8259. Min Act: -0.0000

Data Index: 997663 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 7.4917. Min Range: -7.4917

Max Act: 3.3676. Min Act: -0.0000

Data Index: 833697 (C4 (Web Text))

Max Activating Token Index: 710

Text #13

Max Range: 7.4917. Min Range: -7.4917

Max Act: 3.3635. Min Act: -0.0000

Data Index: 110561 (C4 (Web Text))

Max Activating Token Index: 731

Text #14

Max Range: 7.4917. Min Range: -7.4917

Max Act: 3.4974. Min Act: -0.0001

Data Index: 1181585 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 7.4917. Min Range: -7.4917

Max Act: 3.6469. Min Act: -0.0000

Data Index: 5059 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 7.4917. Min Range: -7.4917

Max Act: 3.5184. Min Act: -0.0001

Data Index: 277902 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 7.4917. Min Range: -7.4917

Max Act: 3.3706. Min Act: -0.0000

Data Index: 252556 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 7.4917. Min Range: -7.4917

Max Act: 3.5199. Min Act: -0.0001

Data Index: 582599 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 7.4917. Min Range: -7.4917

Max Act: 3.0741. Min Act: -0.0001

Data Index: 81281 (C4 (Web Text))

Max Activating Token Index: 757