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

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

Neuron 1384 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: 0.0786. Min Range: -0.0786

Max Act: 0.0786. Min Act: -0.0002

Data Index: 33556 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1413254 (Python Code)

Max Activating Token Index: 308

Text #2

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0749. Min Act: -0.0002

Data Index: 148818 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0750. Min Act: -0.0002

Data Index: 1416420 (Python Code)

Max Activating Token Index: 138

Text #4

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1578150 (Python Code)

Max Activating Token Index: 106

Text #5

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1360224 (Python Code)

Max Activating Token Index: 526

Text #6

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0706. Min Act: -0.0002

Data Index: 1608927 (Python Code)

Max Activating Token Index: 992

Text #7

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0694. Min Act: -0.0002

Data Index: 1448453 (Python Code)

Max Activating Token Index: 903

Text #8

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1400951 (Python Code)

Max Activating Token Index: 400

Text #9

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0713. Min Act: -0.0002

Data Index: 1633685 (Python Code)

Max Activating Token Index: 339

Text #10

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0708. Min Act: -0.0002

Data Index: 1474365 (Python Code)

Max Activating Token Index: 180

Text #11

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0713. Min Act: -0.0002

Data Index: 1649750 (Python Code)

Max Activating Token Index: 945

Text #12

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0701. Min Act: -0.0002

Data Index: 1486838 (Python Code)

Max Activating Token Index: 598

Text #13

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0698. Min Act: -0.0002

Data Index: 1641612 (Python Code)

Max Activating Token Index: 519

Text #14

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1536881 (Python Code)

Max Activating Token Index: 430

Text #15

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0681. Min Act: -0.0002

Data Index: 1651680 (Python Code)

Max Activating Token Index: 829

Text #16

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1592045 (Python Code)

Max Activating Token Index: 637

Text #17

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0661. Min Act: -0.0002

Data Index: 357200 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1592119 (Python Code)

Max Activating Token Index: 648

Text #19

Max Range: 0.0786. Min Range: -0.0786

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1401850 (Python Code)

Max Activating Token Index: 528