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

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

Neuron 3393 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6687. Min Range: -0.6687

Max Act: 0.6568. Min Act: -0.0000

Data Index: 93326 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 0.6687. Min Range: -0.6687

Max Act: 0.6687. Min Act: -0.0000

Data Index: 424275 (C4 (Web Text))

Max Activating Token Index: 343

Text #2

Max Range: 0.6687. Min Range: -0.6687

Max Act: 0.6211. Min Act: -0.0000

Data Index: 970098 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.6687. Min Range: -0.6687

Max Act: 0.5536. Min Act: -0.0000

Data Index: 569404 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 0.6687. Min Range: -0.6687

Max Act: 0.4578. Min Act: -0.0000

Data Index: 668412 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.6687. Min Range: -0.6687

Max Act: 0.4228. Min Act: -0.0000

Data Index: 333892 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.6687. Min Range: -0.6687

Max Act: 0.4667. Min Act: -0.0000

Data Index: 1082654 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.6687. Min Range: -0.6687

Max Act: 0.4263. Min Act: -0.0000

Data Index: 678247 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 0.6687. Min Range: -0.6687

Max Act: 0.4684. Min Act: -0.0000

Data Index: 440660 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 0.6687. Min Range: -0.6687

Max Act: 0.4657. Min Act: -0.0000

Data Index: 1504649 (Python Code)

Max Activating Token Index: 1014

Text #10

Max Range: 0.6687. Min Range: -0.6687

Max Act: 0.4378. Min Act: -0.0000

Data Index: 748281 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 0.6687. Min Range: -0.6687

Max Act: 0.4547. Min Act: -0.0000

Data Index: 1189097 (C4 (Web Text))

Max Activating Token Index: 819

Text #12

Max Range: 0.6687. Min Range: -0.6687

Max Act: 0.3856. Min Act: -0.0000

Data Index: 1469164 (Python Code)

Max Activating Token Index: 885

Text #13

Max Range: 0.6687. Min Range: -0.6687

Max Act: 0.4303. Min Act: -0.0000

Data Index: 1316722 (C4 (Web Text))

Max Activating Token Index: 274

Text #14

Max Range: 0.6687. Min Range: -0.6687

Max Act: 0.3732. Min Act: -0.0000

Data Index: 593226 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 0.6687. Min Range: -0.6687

Max Act: 0.3756. Min Act: -0.0000

Data Index: 596426 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.6687. Min Range: -0.6687

Max Act: 0.3751. Min Act: -0.0000

Data Index: 1381616 (Python Code)

Max Activating Token Index: 319

Text #17

Max Range: 0.6687. Min Range: -0.6687

Max Act: 0.3810. Min Act: -0.0000

Data Index: 243555 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.6687. Min Range: -0.6687

Max Act: 0.3691. Min Act: -0.0000

Data Index: 315983 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 0.6687. Min Range: -0.6687

Max Act: 0.4633. Min Act: -0.0000

Data Index: 818125 (C4 (Web Text))

Max Activating Token Index: 349