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

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

Neuron 1160 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8989. Min Act: -0.0001

Data Index: 1010941 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.9531. Min Act: -0.0001

Data Index: 69724 (C4 (Web Text))

Max Activating Token Index: 134

Text #2

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8621. Min Act: -0.0001

Data Index: 285497 (C4 (Web Text))

Max Activating Token Index: 340

Text #3

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8622. Min Act: -0.0000

Data Index: 466960 (C4 (Web Text))

Max Activating Token Index: 703

Text #4

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.9177. Min Act: -0.0001

Data Index: 601057 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8809. Min Act: -0.0001

Data Index: 495830 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8570. Min Act: -0.0001

Data Index: 205832 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8625. Min Act: -0.0001

Data Index: 1131629 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8228. Min Act: -0.0001

Data Index: 1311806 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8176. Min Act: -0.0001

Data Index: 275434 (C4 (Web Text))

Max Activating Token Index: 232

Text #10

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7955. Min Act: -0.0001

Data Index: 1176048 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.9302. Min Act: -0.0000

Data Index: 532330 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8753. Min Act: -0.0001

Data Index: 562150 (C4 (Web Text))

Max Activating Token Index: 678

Text #13

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8191. Min Act: -0.0001

Data Index: 1006898 (C4 (Web Text))

Max Activating Token Index: 264

Text #14

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7275. Min Act: -0.0001

Data Index: 446182 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7391. Min Act: -0.0001

Data Index: 254992 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7884. Min Act: -0.0000

Data Index: 139439 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8301. Min Act: -0.0001

Data Index: 347359 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.8296. Min Act: -0.0001

Data Index: 1349626 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.9531. Min Range: -0.9531

Max Act: 0.7548. Min Act: -0.0001

Data Index: 1003039 (C4 (Web Text))

Max Activating Token Index: 824