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

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

Neuron 1301 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2221. Min Range: -3.2221

Max Act: 3.2221. Min Act: -0.1700

Data Index: 611743 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 3.2221. Min Range: -3.2221

Max Act: 3.2063. Min Act: -0.1700

Data Index: 895770 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 3.2221. Min Range: -3.2221

Max Act: 3.2063. Min Act: -0.1700

Data Index: 112353 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 3.2221. Min Range: -3.2221

Max Act: 3.1906. Min Act: -0.1700

Data Index: 940641 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 3.2221. Min Range: -3.2221

Max Act: 3.1749. Min Act: -0.1700

Data Index: 263796 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 3.2221. Min Range: -3.2221

Max Act: 3.1749. Min Act: -0.1700

Data Index: 482226 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 3.2221. Min Range: -3.2221

Max Act: 3.1591. Min Act: -0.1700

Data Index: 942801 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 3.2221. Min Range: -3.2221

Max Act: 3.1434. Min Act: -0.1700

Data Index: 869239 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 3.2221. Min Range: -3.2221

Max Act: 3.1434. Min Act: -0.1700

Data Index: 1259955 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 3.2221. Min Range: -3.2221

Max Act: 3.1591. Min Act: -0.1700

Data Index: 1060212 (C4 (Web Text))

Max Activating Token Index: 270

Text #10

Max Range: 3.2221. Min Range: -3.2221

Max Act: 3.1591. Min Act: -0.1700

Data Index: 911270 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 3.2221. Min Range: -3.2221

Max Act: 3.1434. Min Act: -0.1700

Data Index: 165478 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 3.2221. Min Range: -3.2221

Max Act: 3.1591. Min Act: -0.1700

Data Index: 722243 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 3.2221. Min Range: -3.2221

Max Act: 3.1591. Min Act: -0.1700

Data Index: 1355542 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 3.2221. Min Range: -3.2221

Max Act: 3.1434. Min Act: -0.1700

Data Index: 634032 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 3.2221. Min Range: -3.2221

Max Act: 3.1591. Min Act: -0.1700

Data Index: 1249641 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 3.2221. Min Range: -3.2221

Max Act: 3.1276. Min Act: -0.1700

Data Index: 1069620 (C4 (Web Text))

Max Activating Token Index: 636

Text #17

Max Range: 3.2221. Min Range: -3.2221

Max Act: 3.1591. Min Act: -0.1700

Data Index: 212810 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 3.2221. Min Range: -3.2221

Max Act: 3.1118. Min Act: -0.1700

Data Index: 771217 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 3.2221. Min Range: -3.2221

Max Act: 3.1434. Min Act: -0.1700

Data Index: 755574 (C4 (Web Text))

Max Activating Token Index: 773