Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3041 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.7433. Min Range: -1.7433

Max Act: 1.7433. Min Act: -0.0000

Data Index: 328872 (C4 (Web Text))

Max Activating Token Index: 929

Text #1

Max Range: 1.7433. Min Range: -1.7433

Max Act: 1.4295. Min Act: -0.0000

Data Index: 563057 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 1.7433. Min Range: -1.7433

Max Act: 1.3834. Min Act: -0.0000

Data Index: 934784 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 1.7433. Min Range: -1.7433

Max Act: 1.4431. Min Act: -0.0000

Data Index: 335378 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 1.7433. Min Range: -1.7433

Max Act: 1.3458. Min Act: -0.0000

Data Index: 144919 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 1.7433. Min Range: -1.7433

Max Act: 1.1370. Min Act: -0.0000

Data Index: 725418 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 1.7433. Min Range: -1.7433

Max Act: 1.1781. Min Act: -0.0000

Data Index: 1639484 (Python Code)

Max Activating Token Index: 122

Text #7

Max Range: 1.7433. Min Range: -1.7433

Max Act: 1.2421. Min Act: -0.0000

Data Index: 1303186 (C4 (Web Text))

Max Activating Token Index: 6

Text #8

Max Range: 1.7433. Min Range: -1.7433

Max Act: 1.2394. Min Act: -0.0000

Data Index: 1040044 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 1.7433. Min Range: -1.7433

Max Act: 1.2685. Min Act: -0.0000

Data Index: 988982 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 1.7433. Min Range: -1.7433

Max Act: 1.1578. Min Act: -0.0000

Data Index: 51822 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 1.7433. Min Range: -1.7433

Max Act: 1.1908. Min Act: -0.0000

Data Index: 893177 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 1.7433. Min Range: -1.7433

Max Act: 1.1177. Min Act: -0.0000

Data Index: 572515 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 1.7433. Min Range: -1.7433

Max Act: 1.1843. Min Act: -0.0000

Data Index: 1436306 (Python Code)

Max Activating Token Index: 9

Text #14

Max Range: 1.7433. Min Range: -1.7433

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1614309 (Python Code)

Max Activating Token Index: 210

Text #15

Max Range: 1.7433. Min Range: -1.7433

Max Act: 1.1945. Min Act: -0.0000

Data Index: 274750 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 1.7433. Min Range: -1.7433

Max Act: 1.0722. Min Act: -0.0000

Data Index: 1125498 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 1.7433. Min Range: -1.7433

Max Act: 1.0285. Min Act: -0.0000

Data Index: 181506 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 1.7433. Min Range: -1.7433

Max Act: 1.0908. Min Act: -0.0000

Data Index: 73412 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 1.7433. Min Range: -1.7433

Max Act: 1.1178. Min Act: -0.0000

Data Index: 1124996 (C4 (Web Text))

Max Activating Token Index: 196