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

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

Neuron 4949 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.6593. Min Act: -0.0001

Data Index: 795750 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5607. Min Act: -0.0001

Data Index: 1345869 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5986. Min Act: -0.0001

Data Index: 887614 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5363. Min Act: -0.0001

Data Index: 398621 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5775. Min Act: -0.0001

Data Index: 6014 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5892. Min Act: -0.0001

Data Index: 795397 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5609. Min Act: -0.0001

Data Index: 421461 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5578. Min Act: -0.0001

Data Index: 1062297 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5164. Min Act: -0.0001

Data Index: 710903 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5273. Min Act: -0.0001

Data Index: 507720 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5045. Min Act: -0.0001

Data Index: 907918 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5513. Min Act: -0.0001

Data Index: 304011 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.4871. Min Act: -0.0001

Data Index: 350799 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5244. Min Act: -0.0001

Data Index: 264417 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.4952. Min Act: -0.0001

Data Index: 911857 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.4736. Min Act: -0.0001

Data Index: 318152 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.5068. Min Act: -0.0001

Data Index: 866267 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.4898. Min Act: -0.0001

Data Index: 43537 (C4 (Web Text))

Max Activating Token Index: 23

Text #18

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.4988. Min Act: -0.0001

Data Index: 532238 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 0.6593. Min Range: -0.6593

Max Act: 0.4735. Min Act: -0.0001

Data Index: 66558 (C4 (Web Text))

Max Activating Token Index: 104