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

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

Neuron 3457 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4360. Min Range: -3.4360

Max Act: 3.1092. Min Act: -0.0002

Data Index: 319602 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.4360. Min Range: -3.4360

Max Act: 3.4360. Min Act: -0.0001

Data Index: 1189813 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 3.4360. Min Range: -3.4360

Max Act: 3.2501. Min Act: -0.0002

Data Index: 46416 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 3.4360. Min Range: -3.4360

Max Act: 3.1683. Min Act: -0.0001

Data Index: 1347051 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 3.4360. Min Range: -3.4360

Max Act: 3.1634. Min Act: -0.0002

Data Index: 313548 (C4 (Web Text))

Max Activating Token Index: 416

Text #5

Max Range: 3.4360. Min Range: -3.4360

Max Act: 3.0808. Min Act: -0.0002

Data Index: 309966 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 3.4360. Min Range: -3.4360

Max Act: 2.9368. Min Act: -0.0002

Data Index: 881818 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 3.4360. Min Range: -3.4360

Max Act: 3.0217. Min Act: -0.0002

Data Index: 400142 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 3.4360. Min Range: -3.4360

Max Act: 2.8195. Min Act: -0.0002

Data Index: 915039 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 3.4360. Min Range: -3.4360

Max Act: 2.8168. Min Act: -0.0002

Data Index: 42097 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 3.4360. Min Range: -3.4360

Max Act: 2.7852. Min Act: -0.0002

Data Index: 1138219 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 3.4360. Min Range: -3.4360

Max Act: 2.8482. Min Act: -0.0002

Data Index: 755905 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 3.4360. Min Range: -3.4360

Max Act: 2.6507. Min Act: -0.0002

Data Index: 1151935 (C4 (Web Text))

Max Activating Token Index: 280

Text #13

Max Range: 3.4360. Min Range: -3.4360

Max Act: 2.7623. Min Act: -0.0002

Data Index: 729921 (C4 (Web Text))

Max Activating Token Index: 720

Text #14

Max Range: 3.4360. Min Range: -3.4360

Max Act: 2.5619. Min Act: -0.0001

Data Index: 869192 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 3.4360. Min Range: -3.4360

Max Act: 2.5380. Min Act: -0.0002

Data Index: 306842 (C4 (Web Text))

Max Activating Token Index: 795

Text #16

Max Range: 3.4360. Min Range: -3.4360

Max Act: 2.4053. Min Act: -0.0002

Data Index: 168740 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 3.4360. Min Range: -3.4360

Max Act: 2.7006. Min Act: -0.0001

Data Index: 93504 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 3.4360. Min Range: -3.4360

Max Act: 2.2768. Min Act: -0.0002

Data Index: 432382 (C4 (Web Text))

Max Activating Token Index: 800

Text #19

Max Range: 3.4360. Min Range: -3.4360

Max Act: 2.4926. Min Act: -0.0002

Data Index: 473607 (C4 (Web Text))

Max Activating Token Index: 573