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

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

Neuron 994 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: 0.0873. Min Range: -0.0873

Max Act: 0.0873. Min Act: -0.0002

Data Index: 412230 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0654. Min Act: -0.0002

Data Index: 47736 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0640. Min Act: -0.0002

Data Index: 748653 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0635. Min Act: -0.0002

Data Index: 670782 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0611. Min Act: -0.0001

Data Index: 360793 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0586. Min Act: -0.0002

Data Index: 64967 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0591. Min Act: -0.0002

Data Index: 357347 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0575. Min Act: -0.0002

Data Index: 457958 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1339064 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0564. Min Act: -0.0002

Data Index: 15340 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0579. Min Act: -0.0002

Data Index: 939799 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1161272 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0567. Min Act: -0.0002

Data Index: 107637 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0570. Min Act: -0.0002

Data Index: 294403 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0560. Min Act: -0.0002

Data Index: 752983 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0567. Min Act: -0.0002

Data Index: 302291 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0554. Min Act: -0.0002

Data Index: 188551 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1302677 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0556. Min Act: -0.0002

Data Index: 58037 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1122922 (C4 (Web Text))

Max Activating Token Index: 40