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

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

Neuron 4340 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3623. Min Range: -1.3623

Max Act: 1.3623. Min Act: -0.0000

Data Index: 585210 (C4 (Web Text))

Max Activating Token Index: 187

Text #1

Max Range: 1.3623. Min Range: -1.3623

Max Act: 1.1804. Min Act: -0.0000

Data Index: 714282 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 1.3623. Min Range: -1.3623

Max Act: 1.1209. Min Act: -0.0000

Data Index: 1436069 (Python Code)

Max Activating Token Index: 797

Text #3

Max Range: 1.3623. Min Range: -1.3623

Max Act: 1.1725. Min Act: -0.0000

Data Index: 164071 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 1.3623. Min Range: -1.3623

Max Act: 1.1556. Min Act: -0.0000

Data Index: 363041 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 1.3623. Min Range: -1.3623

Max Act: 1.1210. Min Act: -0.0000

Data Index: 556488 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 1.3623. Min Range: -1.3623

Max Act: 1.0822. Min Act: -0.0000

Data Index: 910289 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 1.3623. Min Range: -1.3623

Max Act: 1.1811. Min Act: -0.0000

Data Index: 281237 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 1.3623. Min Range: -1.3623

Max Act: 1.1069. Min Act: -0.0000

Data Index: 1127958 (C4 (Web Text))

Max Activating Token Index: 130

Text #9

Max Range: 1.3623. Min Range: -1.3623

Max Act: 1.1303. Min Act: -0.0000

Data Index: 359878 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 1.3623. Min Range: -1.3623

Max Act: 1.0623. Min Act: -0.0000

Data Index: 23828 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 1.3623. Min Range: -1.3623

Max Act: 1.0526. Min Act: -0.0000

Data Index: 753763 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 1.3623. Min Range: -1.3623

Max Act: 1.0816. Min Act: -0.0000

Data Index: 926811 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 1.3623. Min Range: -1.3623

Max Act: 1.0716. Min Act: -0.0000

Data Index: 502310 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 1.3623. Min Range: -1.3623

Max Act: 1.0635. Min Act: -0.0000

Data Index: 91815 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 1.3623. Min Range: -1.3623

Max Act: 1.0343. Min Act: -0.0000

Data Index: 42701 (C4 (Web Text))

Max Activating Token Index: 116

Text #16

Max Range: 1.3623. Min Range: -1.3623

Max Act: 1.0225. Min Act: -0.0000

Data Index: 822576 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 1.3623. Min Range: -1.3623

Max Act: 1.0499. Min Act: -0.0000

Data Index: 141393 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 1.3623. Min Range: -1.3623

Max Act: 1.0543. Min Act: -0.0000

Data Index: 418297 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 1.3623. Min Range: -1.3623

Max Act: 1.0237. Min Act: -0.0000

Data Index: 829508 (C4 (Web Text))

Max Activating Token Index: 113