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

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

Neuron 428 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0873. Min Act: -0.0001

Data Index: 1060877 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0784. Min Act: -0.0002

Data Index: 925012 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0679. Min Act: -0.0002

Data Index: 188534 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0763. Min Act: -0.0002

Data Index: 215910 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0670. Min Act: -0.0002

Data Index: 444738 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0775. Min Act: -0.0001

Data Index: 546775 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0693. Min Act: -0.0001

Data Index: 1312853 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0625. Min Act: -0.0001

Data Index: 430254 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0669. Min Act: -0.0001

Data Index: 833475 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0706. Min Act: -0.0001

Data Index: 97420 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0632. Min Act: -0.0001

Data Index: 26860 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0701. Min Act: -0.0001

Data Index: 684667 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0616. Min Act: -0.0001

Data Index: 728272 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0664. Min Act: -0.0001

Data Index: 355093 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0625. Min Act: -0.0002

Data Index: 345909 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0686. Min Act: -0.0002

Data Index: 360830 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0614. Min Act: -0.0002

Data Index: 1022431 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0632. Min Act: -0.0002

Data Index: 331616 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0684. Min Act: -0.0001

Data Index: 861722 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.0873. Min Range: -0.0873

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1111971 (C4 (Web Text))

Max Activating Token Index: 141