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

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

Neuron 645 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: 1.9753. Min Range: -1.9753

Max Act: 1.9631. Min Act: -0.0002

Data Index: 933050 (C4 (Web Text))

Max Activating Token Index: 605

Text #1

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.9361. Min Act: -0.0002

Data Index: 169881 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.9631. Min Act: -0.0002

Data Index: 1207911 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.9723. Min Act: -0.0001

Data Index: 120304 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.6743. Min Act: -0.0001

Data Index: 523610 (C4 (Web Text))

Max Activating Token Index: 666

Text #5

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.7283. Min Act: -0.0001

Data Index: 505238 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.8750. Min Act: -0.0001

Data Index: 322926 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.9753. Min Act: -0.0001

Data Index: 689587 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.9590. Min Act: -0.0001

Data Index: 955291 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.7471. Min Act: -0.0002

Data Index: 1053586 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.6589. Min Act: -0.0002

Data Index: 751983 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.7955. Min Act: -0.0002

Data Index: 709679 (C4 (Web Text))

Max Activating Token Index: 97

Text #12

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.6859. Min Act: -0.0001

Data Index: 839938 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.7065. Min Act: -0.0002

Data Index: 1274859 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.7107. Min Act: -0.0002

Data Index: 1185033 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.7258. Min Act: -0.0002

Data Index: 295381 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.7125. Min Act: -0.0001

Data Index: 439266 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.6341. Min Act: -0.0001

Data Index: 1066261 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.5639. Min Act: -0.0002

Data Index: 928200 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 1.9753. Min Range: -1.9753

Max Act: 1.5611. Min Act: -0.0002

Data Index: 1110774 (C4 (Web Text))

Max Activating Token Index: 709