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

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

Neuron 3465 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: 0.5375. Min Range: -0.5375

Max Act: 0.5375. Min Act: -0.0001

Data Index: 67466 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.5292. Min Act: -0.0001

Data Index: 821503 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4737. Min Act: -0.0000

Data Index: 323186 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.5111. Min Act: -0.0000

Data Index: 1175281 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.5286. Min Act: -0.0000

Data Index: 180426 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4779. Min Act: -0.0000

Data Index: 808991 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4971. Min Act: -0.0001

Data Index: 288325 (C4 (Web Text))

Max Activating Token Index: 222

Text #7

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4377. Min Act: -0.0000

Data Index: 531786 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4356. Min Act: -0.0000

Data Index: 758880 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4447. Min Act: -0.0001

Data Index: 381000 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4205. Min Act: -0.0000

Data Index: 1064385 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4296. Min Act: -0.0000

Data Index: 426199 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4712. Min Act: -0.0000

Data Index: 991228 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4353. Min Act: -0.0001

Data Index: 524459 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4658. Min Act: -0.0001

Data Index: 142334 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4095. Min Act: -0.0000

Data Index: 1355262 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4363. Min Act: -0.0000

Data Index: 629353 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4170. Min Act: -0.0000

Data Index: 1138688 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4231. Min Act: -0.0000

Data Index: 77395 (C4 (Web Text))

Max Activating Token Index: 340

Text #19

Max Range: 0.5375. Min Range: -0.5375

Max Act: 0.4363. Min Act: -0.0000

Data Index: 999564 (C4 (Web Text))

Max Activating Token Index: 725