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

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

Neuron 4016 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0991. Min Range: -4.0991

Max Act: 4.0991. Min Act: -0.0000

Data Index: 694828 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 4.0991. Min Range: -4.0991

Max Act: 3.7326. Min Act: -0.0000

Data Index: 1062776 (C4 (Web Text))

Max Activating Token Index: 175

Text #2

Max Range: 4.0991. Min Range: -4.0991

Max Act: 3.6558. Min Act: -0.0000

Data Index: 1047888 (C4 (Web Text))

Max Activating Token Index: 583

Text #3

Max Range: 4.0991. Min Range: -4.0991

Max Act: 3.3164. Min Act: -0.0000

Data Index: 537652 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 4.0991. Min Range: -4.0991

Max Act: 3.4170. Min Act: -0.0000

Data Index: 359799 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 4.0991. Min Range: -4.0991

Max Act: 2.7058. Min Act: -0.0000

Data Index: 825633 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 4.0991. Min Range: -4.0991

Max Act: 3.0971. Min Act: -0.0000

Data Index: 744932 (C4 (Web Text))

Max Activating Token Index: 515

Text #7

Max Range: 4.0991. Min Range: -4.0991

Max Act: 3.2260. Min Act: -0.0000

Data Index: 312215 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 4.0991. Min Range: -4.0991

Max Act: 2.8102. Min Act: -0.0000

Data Index: 944208 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 4.0991. Min Range: -4.0991

Max Act: 2.9047. Min Act: -0.0000

Data Index: 246319 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 4.0991. Min Range: -4.0991

Max Act: 2.9482. Min Act: -0.0000

Data Index: 787322 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 4.0991. Min Range: -4.0991

Max Act: 2.9398. Min Act: -0.0000

Data Index: 1171250 (C4 (Web Text))

Max Activating Token Index: 703

Text #12

Max Range: 4.0991. Min Range: -4.0991

Max Act: 2.9279. Min Act: -0.0000

Data Index: 1327687 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 4.0991. Min Range: -4.0991

Max Act: 2.7675. Min Act: -0.0000

Data Index: 560818 (C4 (Web Text))

Max Activating Token Index: 589

Text #14

Max Range: 4.0991. Min Range: -4.0991

Max Act: 2.7373. Min Act: -0.0000

Data Index: 995557 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 4.0991. Min Range: -4.0991

Max Act: 2.5490. Min Act: -0.0000

Data Index: 16406 (C4 (Web Text))

Max Activating Token Index: 366

Text #16

Max Range: 4.0991. Min Range: -4.0991

Max Act: 2.7846. Min Act: -0.0000

Data Index: 177721 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 4.0991. Min Range: -4.0991

Max Act: 2.6230. Min Act: -0.0000

Data Index: 420079 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 4.0991. Min Range: -4.0991

Max Act: 2.7486. Min Act: -0.0000

Data Index: 979861 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 4.0991. Min Range: -4.0991

Max Act: 2.6018. Min Act: -0.0000

Data Index: 900269 (C4 (Web Text))

Max Activating Token Index: 586