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

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

Neuron 1214 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5720. Min Range: -4.5720

Max Act: 4.5641. Min Act: -0.0000

Data Index: 196213 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 4.5720. Min Range: -4.5720

Max Act: 4.5720. Min Act: -0.0000

Data Index: 1192004 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 4.5720. Min Range: -4.5720

Max Act: 4.1578. Min Act: -0.0000

Data Index: 89869 (C4 (Web Text))

Max Activating Token Index: 267

Text #3

Max Range: 4.5720. Min Range: -4.5720

Max Act: 4.1020. Min Act: -0.0000

Data Index: 380104 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 4.5720. Min Range: -4.5720

Max Act: 4.0379. Min Act: -0.0000

Data Index: 442284 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 4.5720. Min Range: -4.5720

Max Act: 4.0311. Min Act: -0.0000

Data Index: 1016948 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.8432. Min Act: -0.0000

Data Index: 36374 (C4 (Web Text))

Max Activating Token Index: 699

Text #7

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.9812. Min Act: -0.0000

Data Index: 426791 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.6108. Min Act: -0.0000

Data Index: 1187798 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 4.5720. Min Range: -4.5720

Max Act: 4.0659. Min Act: -0.0000

Data Index: 600258 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.8456. Min Act: -0.0000

Data Index: 902746 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.8245. Min Act: 0.0000

Data Index: 1070524 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.8149. Min Act: -0.0000

Data Index: 1015235 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.7971. Min Act: -0.0000

Data Index: 1260607 (C4 (Web Text))

Max Activating Token Index: 429

Text #14

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.5879. Min Act: -0.0000

Data Index: 433899 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.5673. Min Act: -0.0000

Data Index: 558629 (C4 (Web Text))

Max Activating Token Index: 581

Text #16

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.5494. Min Act: -0.0000

Data Index: 636214 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.5611. Min Act: -0.0000

Data Index: 731046 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.7052. Min Act: -0.0000

Data Index: 1191292 (C4 (Web Text))

Max Activating Token Index: 972

Text #19

Max Range: 4.5720. Min Range: -4.5720

Max Act: 3.7125. Min Act: -0.0000

Data Index: 1208990 (C4 (Web Text))

Max Activating Token Index: 662