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

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

Neuron 469 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: 3.3558. Min Range: -3.3558

Max Act: 3.3558. Min Act: -0.1700

Data Index: 735937 (C4 (Web Text))

Max Activating Token Index: 855

Text #1

Max Range: 3.3558. Min Range: -3.3558

Max Act: 3.3087. Min Act: -0.1700

Data Index: 142730 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 3.3558. Min Range: -3.3558

Max Act: 3.2144. Min Act: -0.1700

Data Index: 808096 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 3.3558. Min Range: -3.3558

Max Act: 3.1672. Min Act: -0.1700

Data Index: 1009395 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 3.3558. Min Range: -3.3558

Max Act: 3.1830. Min Act: -0.1700

Data Index: 1292557 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 3.3558. Min Range: -3.3558

Max Act: 3.1515. Min Act: -0.1700

Data Index: 128050 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 3.3558. Min Range: -3.3558

Max Act: 3.1357. Min Act: -0.1700

Data Index: 266290 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 3.3558. Min Range: -3.3558

Max Act: 3.1357. Min Act: -0.1700

Data Index: 1203557 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 3.3558. Min Range: -3.3558

Max Act: 3.1357. Min Act: -0.1700

Data Index: 232327 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 3.3558. Min Range: -3.3558

Max Act: 3.1200. Min Act: -0.1700

Data Index: 1063751 (C4 (Web Text))

Max Activating Token Index: 506

Text #10

Max Range: 3.3558. Min Range: -3.3558

Max Act: 3.1200. Min Act: -0.1700

Data Index: 897266 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 3.3558. Min Range: -3.3558

Max Act: 3.1200. Min Act: -0.1700

Data Index: 785926 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 3.3558. Min Range: -3.3558

Max Act: 3.0884. Min Act: -0.1700

Data Index: 57500 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 3.3558. Min Range: -3.3558

Max Act: 3.1357. Min Act: -0.1700

Data Index: 796182 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 3.3558. Min Range: -3.3558

Max Act: 3.0884. Min Act: -0.1700

Data Index: 828826 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 3.3558. Min Range: -3.3558

Max Act: 3.1200. Min Act: -0.1700

Data Index: 1054244 (C4 (Web Text))

Max Activating Token Index: 796

Text #16

Max Range: 3.3558. Min Range: -3.3558

Max Act: 3.1357. Min Act: -0.1700

Data Index: 1048999 (C4 (Web Text))

Max Activating Token Index: 640

Text #17

Max Range: 3.3558. Min Range: -3.3558

Max Act: 3.0569. Min Act: -0.1700

Data Index: 242666 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 3.3558. Min Range: -3.3558

Max Act: 3.0884. Min Act: -0.1700

Data Index: 961536 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 3.3558. Min Range: -3.3558

Max Act: 3.1042. Min Act: -0.1700

Data Index: 489869 (C4 (Web Text))

Max Activating Token Index: 506