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

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

Neuron 980 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.8411. Min Act: -0.0000

Data Index: 890643 (C4 (Web Text))

Max Activating Token Index: 60

Text #1

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.8375. Min Act: -0.0000

Data Index: 161458 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.8286. Min Act: -0.0000

Data Index: 435700 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.8742. Min Act: -0.0000

Data Index: 421948 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.8155. Min Act: -0.0000

Data Index: 929391 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.8117. Min Act: -0.0000

Data Index: 371138 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7357. Min Act: -0.0000

Data Index: 515218 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7796. Min Act: -0.0000

Data Index: 1135109 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7526. Min Act: -0.0000

Data Index: 96367 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7281. Min Act: -0.0000

Data Index: 1233663 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7027. Min Act: -0.0000

Data Index: 959619 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7393. Min Act: -0.0000

Data Index: 626632 (C4 (Web Text))

Max Activating Token Index: 356

Text #12

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.6793. Min Act: -0.0000

Data Index: 1130255 (C4 (Web Text))

Max Activating Token Index: 597

Text #13

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7042. Min Act: -0.0000

Data Index: 129047 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.7418. Min Act: -0.0000

Data Index: 1242786 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.6598. Min Act: -0.0000

Data Index: 82246 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1029999 (C4 (Web Text))

Max Activating Token Index: 332

Text #17

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.6937. Min Act: -0.0000

Data Index: 1206412 (C4 (Web Text))

Max Activating Token Index: 399

Text #18

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.6868. Min Act: -0.0000

Data Index: 565753 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 0.8742. Min Range: -0.8742

Max Act: 0.6809. Min Act: 0.0000

Data Index: 666636 (C4 (Web Text))

Max Activating Token Index: 228