Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 227 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2773. Min Act: -0.1700

Data Index: 274772 (C4 (Web Text))

Max Activating Token Index: 698

Text #1

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2773. Min Act: -0.1700

Data Index: 162015 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.3087. Min Act: -0.1700

Data Index: 215637 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.3087. Min Act: -0.1700

Data Index: 1230915 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2773. Min Act: -0.1700

Data Index: 89969 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2459. Min Act: -0.1700

Data Index: 871097 (C4 (Web Text))

Max Activating Token Index: 13

Text #6

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2144. Min Act: -0.1700

Data Index: 194412 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2773. Min Act: -0.1700

Data Index: 178121 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2459. Min Act: -0.1700

Data Index: 524305 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2144. Min Act: -0.1700

Data Index: 1195283 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2144. Min Act: -0.1700

Data Index: 747914 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2144. Min Act: -0.1700

Data Index: 787810 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.1515. Min Act: -0.1700

Data Index: 1129159 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.1829. Min Act: -0.1700

Data Index: 283441 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.2144. Min Act: -0.1700

Data Index: 937340 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.1829. Min Act: -0.1700

Data Index: 1015375 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.1829. Min Act: -0.1700

Data Index: 186256 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.1829. Min Act: -0.1700

Data Index: 52826 (C4 (Web Text))

Max Activating Token Index: 871

Text #18

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.1829. Min Act: -0.1700

Data Index: 228097 (C4 (Web Text))

Max Activating Token Index: 30

Text #19

Max Range: 3.3087. Min Range: -3.3087

Max Act: 3.1515. Min Act: -0.1700

Data Index: 1112366 (C4 (Web Text))

Max Activating Token Index: 1023