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

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

Neuron 1034 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0911. Min Act: -0.0002

Data Index: 1377795 (Python Code)

Max Activating Token Index: 962

Text #1

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0863. Min Act: -0.0002

Data Index: 1404787 (Python Code)

Max Activating Token Index: 321

Text #2

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1408514 (Python Code)

Max Activating Token Index: 422

Text #3

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1401223 (Python Code)

Max Activating Token Index: 288

Text #4

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0748. Min Act: -0.0002

Data Index: 1447070 (Python Code)

Max Activating Token Index: 232

Text #5

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0674. Min Act: -0.0002

Data Index: 1419136 (Python Code)

Max Activating Token Index: 227

Text #6

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1397120 (Python Code)

Max Activating Token Index: 558

Text #7

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1588407 (Python Code)

Max Activating Token Index: 383

Text #8

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0690. Min Act: -0.0002

Data Index: 1468941 (Python Code)

Max Activating Token Index: 174

Text #9

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1424596 (Python Code)

Max Activating Token Index: 765

Text #10

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1446330 (Python Code)

Max Activating Token Index: 172

Text #11

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0635. Min Act: -0.0002

Data Index: 1563441 (Python Code)

Max Activating Token Index: 496

Text #12

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0746. Min Act: -0.0002

Data Index: 19288 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0670. Min Act: -0.0002

Data Index: 1404660 (Python Code)

Max Activating Token Index: 213

Text #14

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1398594 (Python Code)

Max Activating Token Index: 639

Text #15

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1448331 (Python Code)

Max Activating Token Index: 87

Text #16

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1503709 (Python Code)

Max Activating Token Index: 90

Text #17

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1601015 (Python Code)

Max Activating Token Index: 498

Text #18

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0658. Min Act: -0.0002

Data Index: 1360601 (Python Code)

Max Activating Token Index: 596

Text #19

Max Range: 0.0911. Min Range: -0.0911

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1587793 (Python Code)

Max Activating Token Index: 237