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

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

Neuron 1609 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0000

Data Index: 295527 (C4 (Web Text))

Max Activating Token Index: 833

Text #1

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0298. Min Act: -0.0000

Data Index: 140985 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0295. Min Act: -0.0000

Data Index: 1400085 (Python Code)

Max Activating Token Index: 622

Text #3

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0292. Min Act: -0.0000

Data Index: 863713 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0305. Min Act: -0.0000

Data Index: 571878 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0286. Min Act: -0.0000

Data Index: 1258841 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0261. Min Act: -0.0000

Data Index: 403575 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0283. Min Act: -0.0000

Data Index: 294820 (C4 (Web Text))

Max Activating Token Index: 553

Text #8

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0265. Min Act: -0.0000

Data Index: 165342 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0258. Min Act: -0.0000

Data Index: 720623 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0259. Min Act: -0.0000

Data Index: 486417 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0250. Min Act: -0.0000

Data Index: 572603 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0275. Min Act: -0.0000

Data Index: 473569 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0246. Min Act: -0.0000

Data Index: 1186809 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0256. Min Act: -0.0000

Data Index: 901259 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0255. Min Act: -0.0000

Data Index: 63189 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0252. Min Act: -0.0000

Data Index: 771708 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0236. Min Act: -0.0000

Data Index: 1152026 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0254. Min Act: -0.0000

Data Index: 279605 (C4 (Web Text))

Max Activating Token Index: 569

Text #19

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0237. Min Act: -0.0000

Data Index: 579730 (C4 (Web Text))

Max Activating Token Index: 328