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

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

Neuron 4482 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0654. Min Range: -1.0654

Max Act: 1.0654. Min Act: -0.0002

Data Index: 759843 (C4 (Web Text))

Max Activating Token Index: 708

Text #1

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.8267. Min Act: -0.0002

Data Index: 803858 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.7706. Min Act: -0.0002

Data Index: 581301 (C4 (Web Text))

Max Activating Token Index: 352

Text #3

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.6852. Min Act: -0.0002

Data Index: 643486 (C4 (Web Text))

Max Activating Token Index: 516

Text #4

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.7296. Min Act: -0.0003

Data Index: 639053 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.6716. Min Act: -0.0002

Data Index: 535660 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.6995. Min Act: -0.0002

Data Index: 825578 (C4 (Web Text))

Max Activating Token Index: 832

Text #7

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.6760. Min Act: -0.0002

Data Index: 1139224 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.8020. Min Act: -0.0002

Data Index: 948219 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.7182. Min Act: -0.0002

Data Index: 1298226 (C4 (Web Text))

Max Activating Token Index: 857

Text #10

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.7085. Min Act: -0.0002

Data Index: 519510 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.7031. Min Act: -0.0002

Data Index: 1013712 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.6820. Min Act: -0.0002

Data Index: 1354409 (C4 (Web Text))

Max Activating Token Index: 131

Text #13

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.6390. Min Act: -0.0002

Data Index: 460608 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.6600. Min Act: -0.0002

Data Index: 1292732 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.6730. Min Act: -0.0002

Data Index: 96183 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.6735. Min Act: -0.0002

Data Index: 1055915 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.6477. Min Act: -0.0002

Data Index: 1271608 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.6609. Min Act: -0.0002

Data Index: 410037 (C4 (Web Text))

Max Activating Token Index: 755

Text #19

Max Range: 1.0654. Min Range: -1.0654

Max Act: 0.6468. Min Act: -0.0002

Data Index: 408957 (C4 (Web Text))

Max Activating Token Index: 950