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

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

Neuron 1390 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.8222. Min Act: -0.0000

Data Index: 137559 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.7523. Min Act: -0.0000

Data Index: 276308 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.7012. Min Act: -0.0000

Data Index: 500090 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6455. Min Act: -0.0000

Data Index: 820640 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6286. Min Act: -0.0000

Data Index: 451109 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.7000. Min Act: -0.0000

Data Index: 1159632 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6363. Min Act: -0.0000

Data Index: 357323 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6827. Min Act: -0.0000

Data Index: 720570 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.7074. Min Act: -0.0000

Data Index: 45825 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.7221. Min Act: -0.0000

Data Index: 867647 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.5809. Min Act: -0.0000

Data Index: 744984 (C4 (Web Text))

Max Activating Token Index: 774

Text #11

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.7004. Min Act: -0.0000

Data Index: 1100784 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.7338. Min Act: -0.0000

Data Index: 1014790 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6995. Min Act: -0.0000

Data Index: 371235 (C4 (Web Text))

Max Activating Token Index: 392

Text #14

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.7080. Min Act: -0.0000

Data Index: 626400 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.5863. Min Act: -0.0000

Data Index: 509960 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6548. Min Act: -0.0000

Data Index: 703237 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.7728. Min Act: -0.0000

Data Index: 130980 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6185. Min Act: -0.0000

Data Index: 855055 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.8222. Min Range: -0.8222

Max Act: 0.6932. Min Act: -0.0000

Data Index: 175485 (C4 (Web Text))

Max Activating Token Index: 847