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

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

Neuron 4782 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0689. Min Act: -0.0001

Data Index: 1028279 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0656. Min Act: -0.0001

Data Index: 54061 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0643. Min Act: -0.0001

Data Index: 5126 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0622. Min Act: -0.0001

Data Index: 690714 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0610. Min Act: -0.0000

Data Index: 10481 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0623. Min Act: -0.0001

Data Index: 1032651 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0601. Min Act: -0.0001

Data Index: 1568972 (Python Code)

Max Activating Token Index: 301

Text #7

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0573. Min Act: -0.0001

Data Index: 400703 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0609. Min Act: -0.0001

Data Index: 787425 (C4 (Web Text))

Max Activating Token Index: 438

Text #9

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0589. Min Act: -0.0001

Data Index: 880910 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0567. Min Act: -0.0001

Data Index: 386709 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0582. Min Act: -0.0001

Data Index: 544103 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0556. Min Act: -0.0001

Data Index: 1307860 (C4 (Web Text))

Max Activating Token Index: 777

Text #13

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0572. Min Act: -0.0001

Data Index: 220513 (C4 (Web Text))

Max Activating Token Index: 1013

Text #14

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0573. Min Act: -0.0001

Data Index: 1285436 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0549. Min Act: -0.0001

Data Index: 1335287 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0562. Min Act: -0.0001

Data Index: 556585 (C4 (Web Text))

Max Activating Token Index: 331

Text #17

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0564. Min Act: -0.0001

Data Index: 542356 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0556. Min Act: -0.0001

Data Index: 1453305 (Python Code)

Max Activating Token Index: 275

Text #19

Max Range: 0.0689. Min Range: -0.0689

Max Act: 0.0556. Min Act: -0.0001

Data Index: 930015 (C4 (Web Text))

Max Activating Token Index: 117