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

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

Neuron 3975 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.5199. Min Act: -0.0000

Data Index: 517441 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.3556. Min Act: -0.0001

Data Index: 1297177 (C4 (Web Text))

Max Activating Token Index: 411

Text #2

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.2599. Min Act: -0.0000

Data Index: 867032 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.1693. Min Act: -0.0001

Data Index: 642416 (C4 (Web Text))

Max Activating Token Index: 526

Text #4

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.1955. Min Act: -0.0000

Data Index: 1353867 (C4 (Web Text))

Max Activating Token Index: 279

Text #5

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.1090. Min Act: -0.0000

Data Index: 432771 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.0953. Min Act: -0.0000

Data Index: 18525 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.0614. Min Act: -0.0000

Data Index: 191092 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.1065. Min Act: -0.0000

Data Index: 1111703 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.1399. Min Act: -0.0000

Data Index: 1245451 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.0699. Min Act: -0.0000

Data Index: 418330 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.0984. Min Act: -0.0001

Data Index: 1437461 (Python Code)

Max Activating Token Index: 659

Text #12

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.0291. Min Act: -0.0000

Data Index: 656303 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.0530. Min Act: -0.0000

Data Index: 253716 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.0469. Min Act: -0.0000

Data Index: 934868 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.0823. Min Act: -0.0000

Data Index: 271740 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.0610. Min Act: -0.0000

Data Index: 1047628 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.1093. Min Act: -0.0000

Data Index: 454929 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 1.5199. Min Range: -1.5199

Max Act: 0.9748. Min Act: -0.0000

Data Index: 997675 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 1.5199. Min Range: -1.5199

Max Act: 1.0555. Min Act: -0.0000

Data Index: 123308 (C4 (Web Text))

Max Activating Token Index: 561