Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2169 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6451. Min Range: -1.6451

Max Act: 1.6451. Min Act: -0.0000

Data Index: 1469859 (Python Code)

Max Activating Token Index: 507

Text #1

Max Range: 1.6451. Min Range: -1.6451

Max Act: 1.5393. Min Act: -0.0000

Data Index: 51075 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 1.6451. Min Range: -1.6451

Max Act: 1.5634. Min Act: -0.0000

Data Index: 471687 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 1.6451. Min Range: -1.6451

Max Act: 1.5154. Min Act: -0.0000

Data Index: 537188 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 1.6451. Min Range: -1.6451

Max Act: 1.3709. Min Act: -0.0000

Data Index: 667748 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 1.6451. Min Range: -1.6451

Max Act: 1.4399. Min Act: -0.0000

Data Index: 440456 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 1.6451. Min Range: -1.6451

Max Act: 1.4862. Min Act: -0.0000

Data Index: 1388148 (Python Code)

Max Activating Token Index: 292

Text #7

Max Range: 1.6451. Min Range: -1.6451

Max Act: 1.3909. Min Act: -0.0000

Data Index: 1202170 (C4 (Web Text))

Max Activating Token Index: 843

Text #8

Max Range: 1.6451. Min Range: -1.6451

Max Act: 1.3730. Min Act: -0.0001

Data Index: 1192771 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 1.6451. Min Range: -1.6451

Max Act: 1.5460. Min Act: -0.0000

Data Index: 1311299 (C4 (Web Text))

Max Activating Token Index: 221

Text #10

Max Range: 1.6451. Min Range: -1.6451

Max Act: 1.3442. Min Act: -0.0000

Data Index: 774452 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 1.6451. Min Range: -1.6451

Max Act: 1.3224. Min Act: -0.0000

Data Index: 787365 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 1.6451. Min Range: -1.6451

Max Act: 1.3669. Min Act: -0.0000

Data Index: 798822 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 1.6451. Min Range: -1.6451

Max Act: 1.4334. Min Act: -0.0000

Data Index: 935573 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 1.6451. Min Range: -1.6451

Max Act: 1.2829. Min Act: -0.0000

Data Index: 1527960 (Python Code)

Max Activating Token Index: 504

Text #15

Max Range: 1.6451. Min Range: -1.6451

Max Act: 1.2596. Min Act: -0.0000

Data Index: 1642903 (Python Code)

Max Activating Token Index: 982

Text #16

Max Range: 1.6451. Min Range: -1.6451

Max Act: 1.1087. Min Act: -0.0000

Data Index: 238779 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 1.6451. Min Range: -1.6451

Max Act: 1.1370. Min Act: -0.0000

Data Index: 123286 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 1.6451. Min Range: -1.6451

Max Act: 1.2397. Min Act: -0.0000

Data Index: 115914 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 1.6451. Min Range: -1.6451

Max Act: 1.2637. Min Act: -0.0000

Data Index: 1172691 (C4 (Web Text))

Max Activating Token Index: 740