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

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

Neuron 3729 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0859. Min Act: -0.0002

Data Index: 633056 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0734. Min Act: -0.0002

Data Index: 1019009 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0789. Min Act: -0.0002

Data Index: 547398 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0700. Min Act: -0.0002

Data Index: 749603 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0746. Min Act: -0.0002

Data Index: 944783 (C4 (Web Text))

Max Activating Token Index: 1007

Text #5

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1471750 (Python Code)

Max Activating Token Index: 303

Text #6

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1427519 (Python Code)

Max Activating Token Index: 79

Text #7

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1104574 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0668. Min Act: -0.0002

Data Index: 185929 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0663. Min Act: -0.0002

Data Index: 222164 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0610. Min Act: -0.0002

Data Index: 1361002 (Python Code)

Max Activating Token Index: 30

Text #11

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0650. Min Act: -0.0002

Data Index: 1367174 (Python Code)

Max Activating Token Index: 383

Text #12

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1341022 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0641. Min Act: -0.0002

Data Index: 1451478 (Python Code)

Max Activating Token Index: 248

Text #14

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1468600 (Python Code)

Max Activating Token Index: 121

Text #15

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0644. Min Act: -0.0002

Data Index: 928949 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1319354 (C4 (Web Text))

Max Activating Token Index: 1003

Text #17

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0588. Min Act: -0.0002

Data Index: 1633688 (Python Code)

Max Activating Token Index: 588

Text #18

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1616888 (Python Code)

Max Activating Token Index: 449

Text #19

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0669. Min Act: -0.0002

Data Index: 1518154 (Python Code)

Max Activating Token Index: 776