Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1818 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0709. Min Act: -0.0002

Data Index: 1462853 (Python Code)

Max Activating Token Index: 245

Text #1

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1379489 (Python Code)

Max Activating Token Index: 984

Text #2

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1373655 (Python Code)

Max Activating Token Index: 562

Text #3

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0640. Min Act: -0.0002

Data Index: 1619872 (Python Code)

Max Activating Token Index: 157

Text #4

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1644556 (Python Code)

Max Activating Token Index: 950

Text #5

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1631683 (Python Code)

Max Activating Token Index: 286

Text #6

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0636. Min Act: -0.0002

Data Index: 1462133 (Python Code)

Max Activating Token Index: 840

Text #7

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1455715 (Python Code)

Max Activating Token Index: 693

Text #8

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1425824 (Python Code)

Max Activating Token Index: 761

Text #9

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1437839 (Python Code)

Max Activating Token Index: 706

Text #10

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1316362 (C4 (Web Text))

Max Activating Token Index: 601

Text #11

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1478683 (Python Code)

Max Activating Token Index: 131

Text #12

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1494713 (Python Code)

Max Activating Token Index: 823

Text #13

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0571. Min Act: -0.0002

Data Index: 1393181 (Python Code)

Max Activating Token Index: 369

Text #14

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0564. Min Act: -0.0002

Data Index: 1392993 (Python Code)

Max Activating Token Index: 796

Text #15

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0555. Min Act: -0.0002

Data Index: 996102 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0565. Min Act: -0.0002

Data Index: 1411417 (Python Code)

Max Activating Token Index: 907

Text #17

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0550. Min Act: -0.0003

Data Index: 1468088 (Python Code)

Max Activating Token Index: 335

Text #18

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1450590 (Python Code)

Max Activating Token Index: 629

Text #19

Max Range: 0.0709. Min Range: -0.0709

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1591960 (Python Code)

Max Activating Token Index: 382