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

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

Neuron 1245 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: 0.0729. Min Range: -0.0729

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1522476 (Python Code)

Max Activating Token Index: 553

Text #1

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0679. Min Act: -0.0002

Data Index: 1634901 (Python Code)

Max Activating Token Index: 507

Text #2

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1521192 (Python Code)

Max Activating Token Index: 240

Text #3

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0633. Min Act: -0.0002

Data Index: 1434861 (Python Code)

Max Activating Token Index: 153

Text #4

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0604. Min Act: -0.0002

Data Index: 1532921 (Python Code)

Max Activating Token Index: 738

Text #5

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1601612 (Python Code)

Max Activating Token Index: 801

Text #6

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0598. Min Act: -0.0002

Data Index: 39598 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0595. Min Act: -0.0002

Data Index: 1501226 (Python Code)

Max Activating Token Index: 948

Text #8

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0615. Min Act: -0.0002

Data Index: 395593 (C4 (Web Text))

Max Activating Token Index: 410

Text #9

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1476383 (Python Code)

Max Activating Token Index: 391

Text #10

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0575. Min Act: -0.0002

Data Index: 570421 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0626. Min Act: -0.0002

Data Index: 1568913 (Python Code)

Max Activating Token Index: 970

Text #12

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0585. Min Act: -0.0002

Data Index: 1475524 (Python Code)

Max Activating Token Index: 699

Text #13

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0565. Min Act: -0.0002

Data Index: 495549 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0562. Min Act: -0.0002

Data Index: 801640 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1427469 (Python Code)

Max Activating Token Index: 910

Text #16

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0578. Min Act: -0.0002

Data Index: 1423743 (Python Code)

Max Activating Token Index: 383

Text #17

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1461744 (Python Code)

Max Activating Token Index: 424

Text #18

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1637866 (Python Code)

Max Activating Token Index: 719

Text #19

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0571. Min Act: -0.0002

Data Index: 1647029 (Python Code)

Max Activating Token Index: 701