Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 42 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0368. Min Act: -0.0002

Data Index: 91714 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1551433 (Python Code)

Max Activating Token Index: 618

Text #2

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0314. Min Act: -0.0002

Data Index: 247052 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1073016 (C4 (Web Text))

Max Activating Token Index: 675

Text #4

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1193296 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0303. Min Act: -0.0002

Data Index: 316130 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0299. Min Act: -0.0002

Data Index: 569077 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1501250 (Python Code)

Max Activating Token Index: 465

Text #8

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0287. Min Act: -0.0000

Data Index: 619882 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0276. Min Act: -0.0002

Data Index: 610085 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0281. Min Act: -0.0002

Data Index: 145242 (C4 (Web Text))

Max Activating Token Index: 880

Text #11

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0282. Min Act: -0.0002

Data Index: 997308 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1558041 (Python Code)

Max Activating Token Index: 177

Text #13

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1544995 (Python Code)

Max Activating Token Index: 724

Text #14

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0268. Min Act: -0.0001

Data Index: 1549951 (Python Code)

Max Activating Token Index: 628

Text #15

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0266. Min Act: -0.0001

Data Index: 507163 (C4 (Web Text))

Max Activating Token Index: 782

Text #16

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1465033 (Python Code)

Max Activating Token Index: 576

Text #17

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1593474 (Python Code)

Max Activating Token Index: 700

Text #18

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0263. Min Act: -0.0002

Data Index: 1644316 (Python Code)

Max Activating Token Index: 499

Text #19

Max Range: 0.0368. Min Range: -0.0368

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1650969 (Python Code)

Max Activating Token Index: 527