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

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

Neuron 3847 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3096. Min Range: -1.3096

Max Act: 1.3096. Min Act: -0.0000

Data Index: 696518 (C4 (Web Text))

Max Activating Token Index: 135

Text #1

Max Range: 1.3096. Min Range: -1.3096

Max Act: 1.0176. Min Act: -0.0000

Data Index: 1586658 (Python Code)

Max Activating Token Index: 144

Text #2

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.9926. Min Act: -0.0000

Data Index: 656317 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 1.3096. Min Range: -1.3096

Max Act: 1.1404. Min Act: -0.0000

Data Index: 1147635 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 1.3096. Min Range: -1.3096

Max Act: 1.0547. Min Act: -0.0000

Data Index: 324945 (C4 (Web Text))

Max Activating Token Index: 252

Text #5

Max Range: 1.3096. Min Range: -1.3096

Max Act: 1.0968. Min Act: -0.0000

Data Index: 876484 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.9811. Min Act: -0.0000

Data Index: 631645 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 1.3096. Min Range: -1.3096

Max Act: 1.1010. Min Act: -0.0000

Data Index: 1279829 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 1.3096. Min Range: -1.3096

Max Act: 1.0256. Min Act: -0.0000

Data Index: 237122 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.9616. Min Act: -0.0000

Data Index: 942360 (C4 (Web Text))

Max Activating Token Index: 828

Text #10

Max Range: 1.3096. Min Range: -1.3096

Max Act: 1.2388. Min Act: -0.0000

Data Index: 84998 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.9229. Min Act: -0.0000

Data Index: 821817 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.9452. Min Act: -0.0000

Data Index: 1255712 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.9270. Min Act: -0.0000

Data Index: 627578 (C4 (Web Text))

Max Activating Token Index: 267

Text #14

Max Range: 1.3096. Min Range: -1.3096

Max Act: 1.0278. Min Act: -0.0000

Data Index: 1379494 (Python Code)

Max Activating Token Index: 376

Text #15

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.9260. Min Act: -0.0000

Data Index: 197203 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.9620. Min Act: -0.0000

Data Index: 1346186 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.9614. Min Act: -0.0000

Data Index: 1053868 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.9638. Min Act: -0.0000

Data Index: 370026 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 1.3096. Min Range: -1.3096

Max Act: 0.9338. Min Act: -0.0000

Data Index: 1531608 (Python Code)

Max Activating Token Index: 153