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

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

Neuron 3814 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0331. Min Range: -2.0331

Max Act: 2.0331. Min Act: -0.0000

Data Index: 1005937 (C4 (Web Text))

Max Activating Token Index: 739

Text #1

Max Range: 2.0331. Min Range: -2.0331

Max Act: 1.9249. Min Act: -0.0000

Data Index: 1032107 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 2.0331. Min Range: -2.0331

Max Act: 1.5669. Min Act: -0.0000

Data Index: 1265812 (C4 (Web Text))

Max Activating Token Index: 777

Text #3

Max Range: 2.0331. Min Range: -2.0331

Max Act: 1.6344. Min Act: -0.0000

Data Index: 216233 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 2.0331. Min Range: -2.0331

Max Act: 1.5251. Min Act: -0.0000

Data Index: 576338 (C4 (Web Text))

Max Activating Token Index: 959

Text #5

Max Range: 2.0331. Min Range: -2.0331

Max Act: 1.4446. Min Act: -0.0000

Data Index: 1044227 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 2.0331. Min Range: -2.0331

Max Act: 1.3049. Min Act: -0.0000

Data Index: 850627 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 2.0331. Min Range: -2.0331

Max Act: 1.3443. Min Act: -0.0000

Data Index: 804933 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 2.0331. Min Range: -2.0331

Max Act: 1.3178. Min Act: -0.0000

Data Index: 1157233 (C4 (Web Text))

Max Activating Token Index: 263

Text #9

Max Range: 2.0331. Min Range: -2.0331

Max Act: 1.3964. Min Act: -0.0000

Data Index: 999078 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 2.0331. Min Range: -2.0331

Max Act: 1.2826. Min Act: -0.0000

Data Index: 1008632 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 2.0331. Min Range: -2.0331

Max Act: 1.2593. Min Act: -0.0000

Data Index: 1273985 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 2.0331. Min Range: -2.0331

Max Act: 1.2627. Min Act: -0.0000

Data Index: 1176407 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 2.0331. Min Range: -2.0331

Max Act: 1.2347. Min Act: -0.0000

Data Index: 1162295 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 2.0331. Min Range: -2.0331

Max Act: 1.2127. Min Act: -0.0000

Data Index: 1124105 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 2.0331. Min Range: -2.0331

Max Act: 1.2019. Min Act: -0.0000

Data Index: 1349782 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 2.0331. Min Range: -2.0331

Max Act: 1.2620. Min Act: -0.0000

Data Index: 35091 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 2.0331. Min Range: -2.0331

Max Act: 1.1116. Min Act: -0.0000

Data Index: 905424 (C4 (Web Text))

Max Activating Token Index: 686

Text #18

Max Range: 2.0331. Min Range: -2.0331

Max Act: 1.1637. Min Act: -0.0000

Data Index: 1069893 (C4 (Web Text))

Max Activating Token Index: 995

Text #19

Max Range: 2.0331. Min Range: -2.0331

Max Act: 1.1584. Min Act: -0.0000

Data Index: 246432 (C4 (Web Text))

Max Activating Token Index: 188