Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3338 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.1012. Min Act: -0.0001

Data Index: 347299 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0823. Min Act: -0.0001

Data Index: 1324732 (C4 (Web Text))

Max Activating Token Index: 312

Text #2

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0667. Min Act: -0.0001

Data Index: 350453 (C4 (Web Text))

Max Activating Token Index: 544

Text #3

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0681. Min Act: -0.0001

Data Index: 1052857 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0652. Min Act: -0.0001

Data Index: 504948 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0629. Min Act: -0.0001

Data Index: 648154 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0588. Min Act: -0.0001

Data Index: 1248183 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0671. Min Act: -0.0001

Data Index: 1338896 (C4 (Web Text))

Max Activating Token Index: 457

Text #8

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0624. Min Act: -0.0001

Data Index: 434296 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0642. Min Act: -0.0001

Data Index: 909206 (C4 (Web Text))

Max Activating Token Index: 207

Text #10

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0572. Min Act: -0.0001

Data Index: 1176890 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0663. Min Act: -0.0001

Data Index: 415504 (C4 (Web Text))

Max Activating Token Index: 245

Text #12

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0639. Min Act: -0.0001

Data Index: 26764 (C4 (Web Text))

Max Activating Token Index: 783

Text #13

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0633. Min Act: -0.0001

Data Index: 659085 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0635. Min Act: -0.0001

Data Index: 107214 (C4 (Web Text))

Max Activating Token Index: 247

Text #15

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0569. Min Act: -0.0001

Data Index: 1234444 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0599. Min Act: -0.0001

Data Index: 524862 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1094486 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0602. Min Act: -0.0001

Data Index: 288577 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.1012. Min Range: -0.1012

Max Act: 0.0678. Min Act: -0.0001

Data Index: 308953 (C4 (Web Text))

Max Activating Token Index: 737