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

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

Neuron 2170 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2017. Min Range: -1.2017

Max Act: 1.2017. Min Act: -0.0000

Data Index: 1179499 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 1.2017. Min Range: -1.2017

Max Act: 1.1425. Min Act: -0.0000

Data Index: 163281 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 1.2017. Min Range: -1.2017

Max Act: 1.1855. Min Act: -0.0000

Data Index: 95698 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 1.2017. Min Range: -1.2017

Max Act: 1.0040. Min Act: -0.0000

Data Index: 1007800 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 1.2017. Min Range: -1.2017

Max Act: 1.0338. Min Act: -0.0000

Data Index: 911981 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 1.2017. Min Range: -1.2017

Max Act: 0.9678. Min Act: -0.0000

Data Index: 1216475 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 1.2017. Min Range: -1.2017

Max Act: 0.9601. Min Act: -0.0000

Data Index: 705144 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 1.2017. Min Range: -1.2017

Max Act: 0.9811. Min Act: -0.0000

Data Index: 863567 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 1.2017. Min Range: -1.2017

Max Act: 1.0480. Min Act: -0.0000

Data Index: 199935 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 1.2017. Min Range: -1.2017

Max Act: 1.0109. Min Act: -0.0000

Data Index: 563326 (C4 (Web Text))

Max Activating Token Index: 693

Text #10

Max Range: 1.2017. Min Range: -1.2017

Max Act: 0.9459. Min Act: -0.0000

Data Index: 1215106 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 1.2017. Min Range: -1.2017

Max Act: 0.9456. Min Act: -0.0000

Data Index: 914184 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 1.2017. Min Range: -1.2017

Max Act: 0.9625. Min Act: -0.0000

Data Index: 426373 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 1.2017. Min Range: -1.2017

Max Act: 0.9201. Min Act: -0.0000

Data Index: 10213 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 1.2017. Min Range: -1.2017

Max Act: 0.9218. Min Act: -0.0000

Data Index: 233061 (C4 (Web Text))

Max Activating Token Index: 490

Text #15

Max Range: 1.2017. Min Range: -1.2017

Max Act: 0.8395. Min Act: -0.0000

Data Index: 256905 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 1.2017. Min Range: -1.2017

Max Act: 0.8928. Min Act: -0.0000

Data Index: 565245 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.2017. Min Range: -1.2017

Max Act: 0.9066. Min Act: -0.0000

Data Index: 702709 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 1.2017. Min Range: -1.2017

Max Act: 0.9042. Min Act: -0.0000

Data Index: 739614 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 1.2017. Min Range: -1.2017

Max Act: 0.8707. Min Act: -0.0000

Data Index: 525881 (C4 (Web Text))

Max Activating Token Index: 450