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

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

Neuron 1040 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1290. Min Act: -0.0002

Data Index: 669003 (C4 (Web Text))

Max Activating Token Index: 808

Text #1

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1243. Min Act: -0.0002

Data Index: 753934 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1039. Min Act: -0.0002

Data Index: 87271 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1028. Min Act: -0.0002

Data Index: 674855 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1036. Min Act: -0.0002

Data Index: 79883 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0955. Min Act: -0.0002

Data Index: 300504 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1011. Min Act: -0.0002

Data Index: 588287 (C4 (Web Text))

Max Activating Token Index: 529

Text #7

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.1005. Min Act: -0.0002

Data Index: 218946 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0959. Min Act: -0.0002

Data Index: 783131 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0983. Min Act: -0.0002

Data Index: 1159504 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0944. Min Act: -0.0002

Data Index: 97767 (C4 (Web Text))

Max Activating Token Index: 169

Text #11

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0937. Min Act: -0.0002

Data Index: 242132 (C4 (Web Text))

Max Activating Token Index: 41

Text #12

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0974. Min Act: -0.0002

Data Index: 276425 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0915. Min Act: -0.0002

Data Index: 15080 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0797. Min Act: -0.0002

Data Index: 1095499 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0856. Min Act: -0.0002

Data Index: 253910 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0784. Min Act: -0.0002

Data Index: 544477 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0847. Min Act: -0.0002

Data Index: 427506 (C4 (Web Text))

Max Activating Token Index: 981

Text #18

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0781. Min Act: -0.0002

Data Index: 59776 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 0.1290. Min Range: -0.1290

Max Act: 0.0813. Min Act: -0.0002

Data Index: 779029 (C4 (Web Text))

Max Activating Token Index: 360