Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 871 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.8167. Min Act: -0.1700

Data Index: 1314689 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.7478. Min Act: -0.1700

Data Index: 1253297 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.7305. Min Act: -0.1700

Data Index: 16194 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.7219. Min Act: -0.1700

Data Index: 1065303 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.7305. Min Act: -0.1700

Data Index: 327719 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.7046. Min Act: -0.1700

Data Index: 127857 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.6959. Min Act: -0.1700

Data Index: 1195138 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.6872. Min Act: -0.1700

Data Index: 576730 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.6959. Min Act: -0.1700

Data Index: 1176258 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.6959. Min Act: -0.1700

Data Index: 289225 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.6959. Min Act: -0.1700

Data Index: 96779 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.6872. Min Act: -0.1700

Data Index: 557263 (C4 (Web Text))

Max Activating Token Index: 992

Text #12

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.6872. Min Act: -0.1700

Data Index: 1251094 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.6872. Min Act: -0.1700

Data Index: 506182 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.6786. Min Act: -0.1700

Data Index: 157622 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.6872. Min Act: -0.1700

Data Index: 987319 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.6786. Min Act: -0.1700

Data Index: 669488 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.6786. Min Act: -0.1699

Data Index: 1177015 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.6699. Min Act: -0.1699

Data Index: 845827 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 1.8167. Min Range: -1.8167

Max Act: 1.6699. Min Act: -0.1700

Data Index: 917659 (C4 (Web Text))

Max Activating Token Index: 1023