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

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

Neuron 2912 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: 1.3560. Min Range: -1.3560

Max Act: 1.3082. Min Act: -0.0000

Data Index: 1274908 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 1.3560. Min Range: -1.3560

Max Act: 1.3560. Min Act: -0.0000

Data Index: 513905 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 1.3560. Min Range: -1.3560

Max Act: 1.2574. Min Act: -0.0000

Data Index: 802646 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 1.3560. Min Range: -1.3560

Max Act: 1.1358. Min Act: -0.0000

Data Index: 439076 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 1.3560. Min Range: -1.3560

Max Act: 1.1155. Min Act: -0.0000

Data Index: 1563004 (Python Code)

Max Activating Token Index: 213

Text #5

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.9960. Min Act: -0.0000

Data Index: 1465402 (Python Code)

Max Activating Token Index: 298

Text #6

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1095466 (C4 (Web Text))

Max Activating Token Index: 29

Text #7

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.9237. Min Act: -0.0000

Data Index: 1474425 (Python Code)

Max Activating Token Index: 703

Text #8

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.9290. Min Act: -0.0000

Data Index: 170481 (C4 (Web Text))

Max Activating Token Index: 244

Text #9

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.8908. Min Act: -0.0000

Data Index: 1656155 (Python Code)

Max Activating Token Index: 143

Text #10

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.9251. Min Act: -0.0000

Data Index: 1518005 (Python Code)

Max Activating Token Index: 782

Text #11

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.9013. Min Act: -0.0000

Data Index: 1460346 (Python Code)

Max Activating Token Index: 1005

Text #12

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.8551. Min Act: -0.0000

Data Index: 1643961 (Python Code)

Max Activating Token Index: 216

Text #13

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.8512. Min Act: -0.0000

Data Index: 1175268 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.8880. Min Act: -0.0000

Data Index: 1647816 (Python Code)

Max Activating Token Index: 378

Text #15

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.8546. Min Act: -0.0000

Data Index: 385218 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.9036. Min Act: -0.0000

Data Index: 1110053 (C4 (Web Text))

Max Activating Token Index: 935

Text #17

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1295211 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.8718. Min Act: -0.0000

Data Index: 935845 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 1.3560. Min Range: -1.3560

Max Act: 0.8984. Min Act: -0.0000

Data Index: 1519505 (Python Code)

Max Activating Token Index: 85