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

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

Neuron 4063 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5338. Min Range: -4.5338

Max Act: 4.3664. Min Act: -0.0000

Data Index: 715581 (C4 (Web Text))

Max Activating Token Index: 251

Text #1

Max Range: 4.5338. Min Range: -4.5338

Max Act: 4.3455. Min Act: -0.0000

Data Index: 573537 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 4.5338. Min Range: -4.5338

Max Act: 4.5338. Min Act: -0.0000

Data Index: 129411 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 4.5338. Min Range: -4.5338

Max Act: 4.3614. Min Act: -0.0000

Data Index: 579295 (C4 (Web Text))

Max Activating Token Index: 468

Text #4

Max Range: 4.5338. Min Range: -4.5338

Max Act: 4.2755. Min Act: -0.0000

Data Index: 205987 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 4.5338. Min Range: -4.5338

Max Act: 4.2421. Min Act: -0.0000

Data Index: 312605 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 4.5338. Min Range: -4.5338

Max Act: 4.2116. Min Act: -0.0000

Data Index: 1095023 (C4 (Web Text))

Max Activating Token Index: 363

Text #7

Max Range: 4.5338. Min Range: -4.5338

Max Act: 4.0174. Min Act: -0.0000

Data Index: 1292136 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 4.5338. Min Range: -4.5338

Max Act: 3.7859. Min Act: -0.0000

Data Index: 35707 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 4.5338. Min Range: -4.5338

Max Act: 3.8478. Min Act: -0.0000

Data Index: 837833 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 4.5338. Min Range: -4.5338

Max Act: 3.9776. Min Act: -0.0000

Data Index: 1125186 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 4.5338. Min Range: -4.5338

Max Act: 3.9911. Min Act: -0.0000

Data Index: 961661 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 4.5338. Min Range: -4.5338

Max Act: 3.7851. Min Act: -0.0000

Data Index: 561891 (C4 (Web Text))

Max Activating Token Index: 211

Text #13

Max Range: 4.5338. Min Range: -4.5338

Max Act: 3.8000. Min Act: -0.0000

Data Index: 1308711 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 4.5338. Min Range: -4.5338

Max Act: 3.6216. Min Act: -0.0000

Data Index: 591149 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 4.5338. Min Range: -4.5338

Max Act: 3.7702. Min Act: -0.0000

Data Index: 17598 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 4.5338. Min Range: -4.5338

Max Act: 3.9000. Min Act: -0.0000

Data Index: 228015 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 4.5338. Min Range: -4.5338

Max Act: 3.9142. Min Act: -0.0000

Data Index: 712785 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 4.5338. Min Range: -4.5338

Max Act: 3.8658. Min Act: -0.0000

Data Index: 1199202 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 4.5338. Min Range: -4.5338

Max Act: 3.3513. Min Act: -0.0000

Data Index: 43002 (C4 (Web Text))

Max Activating Token Index: 236