Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1383 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1615. Min Act: -0.0001

Data Index: 322522 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1776. Min Act: -0.0001

Data Index: 1365577 (Python Code)

Max Activating Token Index: 505

Text #2

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1675. Min Act: -0.0001

Data Index: 1405737 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1389. Min Act: -0.0001

Data Index: 1306134 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1215. Min Act: -0.0001

Data Index: 1004838 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1046. Min Act: -0.0001

Data Index: 1056471 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.0990. Min Act: -0.0001

Data Index: 101308 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1037. Min Act: -0.0001

Data Index: 588021 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.0874. Min Act: -0.0001

Data Index: 230119 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.0851. Min Act: -0.0001

Data Index: 358068 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.0744. Min Act: -0.0001

Data Index: 663584 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.0781. Min Act: -0.0001

Data Index: 1008227 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1299777 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1010886 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.0614. Min Act: -0.0001

Data Index: 613584 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.0672. Min Act: -0.0001

Data Index: 1540841 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.0635. Min Act: -0.0001

Data Index: 588940 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1308 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.0773. Min Act: -0.0001

Data Index: 280032 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 0.1776. Min Range: -0.1776

Max Act: 0.0527. Min Act: -0.0001

Data Index: 1526280 (Python Code)

Max Activating Token Index: 899