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

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

Neuron 5670 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2126. Min Range: -1.2126

Max Act: 1.2126. Min Act: 0.0000

Data Index: 158719 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 1.2126. Min Range: -1.2126

Max Act: 1.2115. Min Act: -0.0000

Data Index: 489058 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 1.2126. Min Range: -1.2126

Max Act: 1.1838. Min Act: -0.0000

Data Index: 767184 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 1.2126. Min Range: -1.2126

Max Act: 1.2029. Min Act: -0.0000

Data Index: 657165 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 1.2126. Min Range: -1.2126

Max Act: 1.1142. Min Act: 0.0001

Data Index: 1023182 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 1.2126. Min Range: -1.2126

Max Act: 1.0873. Min Act: -0.0000

Data Index: 838991 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 1.2126. Min Range: -1.2126

Max Act: 1.0670. Min Act: -0.0000

Data Index: 848094 (C4 (Web Text))

Max Activating Token Index: 918

Text #7

Max Range: 1.2126. Min Range: -1.2126

Max Act: 1.0283. Min Act: -0.0000

Data Index: 723436 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 1.2126. Min Range: -1.2126

Max Act: 1.0215. Min Act: -0.0000

Data Index: 429381 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 1.2126. Min Range: -1.2126

Max Act: 1.0173. Min Act: -0.0000

Data Index: 1177232 (C4 (Web Text))

Max Activating Token Index: 749

Text #10

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.9549. Min Act: -0.0000

Data Index: 138001 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 1.2126. Min Range: -1.2126

Max Act: 1.0015. Min Act: -0.0000

Data Index: 1291663 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.9780. Min Act: -0.0000

Data Index: 673944 (C4 (Web Text))

Max Activating Token Index: 477

Text #13

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.9610. Min Act: -0.0000

Data Index: 1198005 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.9375. Min Act: -0.0000

Data Index: 866520 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.8770. Min Act: -0.0000

Data Index: 1067742 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.9315. Min Act: -0.0000

Data Index: 765247 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.9197. Min Act: -0.0000

Data Index: 10638 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.9265. Min Act: -0.0000

Data Index: 429673 (C4 (Web Text))

Max Activating Token Index: 802

Text #19

Max Range: 1.2126. Min Range: -1.2126

Max Act: 0.9135. Min Act: -0.0000

Data Index: 768003 (C4 (Web Text))

Max Activating Token Index: 264