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

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

Neuron 693 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: 0.0772. Min Range: -0.0772

Max Act: 0.0772. Min Act: -0.0001

Data Index: 74880 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0704. Min Act: -0.0002

Data Index: 466486 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0689. Min Act: -0.0002

Data Index: 33250 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0669. Min Act: -0.0001

Data Index: 263621 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0676. Min Act: -0.0002

Data Index: 1386957 (Python Code)

Max Activating Token Index: 211

Text #5

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0671. Min Act: -0.0002

Data Index: 1578015 (Python Code)

Max Activating Token Index: 891

Text #6

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0644. Min Act: -0.0002

Data Index: 635306 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0648. Min Act: -0.0002

Data Index: 471439 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0610. Min Act: -0.0002

Data Index: 213257 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0633. Min Act: -0.0002

Data Index: 387127 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0619. Min Act: -0.0002

Data Index: 982715 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0626. Min Act: -0.0002

Data Index: 1291121 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0623. Min Act: -0.0001

Data Index: 523844 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0627. Min Act: -0.0001

Data Index: 93797 (C4 (Web Text))

Max Activating Token Index: 84

Text #14

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0603. Min Act: -0.0002

Data Index: 477690 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0605. Min Act: -0.0002

Data Index: 175526 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0624. Min Act: -0.0002

Data Index: 306264 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0602. Min Act: -0.0001

Data Index: 684119 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1347146 (C4 (Web Text))

Max Activating Token Index: 598

Text #19

Max Range: 0.0772. Min Range: -0.0772

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1162384 (C4 (Web Text))

Max Activating Token Index: 184