Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1698 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.8140. Min Range: -3.8140

Max Act: 3.8140. Min Act: -0.1700

Data Index: 1316358 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 3.8140. Min Range: -3.8140

Max Act: 3.7827. Min Act: -0.1700

Data Index: 307908 (C4 (Web Text))

Max Activating Token Index: 635

Text #2

Max Range: 3.8140. Min Range: -3.8140

Max Act: 3.7827. Min Act: -0.1700

Data Index: 1625062 (Python Code)

Max Activating Token Index: 42

Text #3

Max Range: 3.8140. Min Range: -3.8140

Max Act: 3.7514. Min Act: -0.1700

Data Index: 1036415 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 3.8140. Min Range: -3.8140

Max Act: 3.7514. Min Act: -0.1700

Data Index: 728218 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 3.8140. Min Range: -3.8140

Max Act: 3.7201. Min Act: -0.1700

Data Index: 1044823 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 3.8140. Min Range: -3.8140

Max Act: 3.6888. Min Act: -0.1700

Data Index: 1203848 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 3.8140. Min Range: -3.8140

Max Act: 3.7514. Min Act: -0.1700

Data Index: 55014 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 3.8140. Min Range: -3.8140

Max Act: 3.6888. Min Act: -0.1700

Data Index: 714971 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 3.8140. Min Range: -3.8140

Max Act: 3.6888. Min Act: -0.1700

Data Index: 88462 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 3.8140. Min Range: -3.8140

Max Act: 3.6732. Min Act: -0.1700

Data Index: 18941 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 3.8140. Min Range: -3.8140

Max Act: 3.6732. Min Act: -0.1700

Data Index: 446477 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 3.8140. Min Range: -3.8140

Max Act: 3.6732. Min Act: -0.1700

Data Index: 1299859 (C4 (Web Text))

Max Activating Token Index: 164

Text #13

Max Range: 3.8140. Min Range: -3.8140

Max Act: 3.6732. Min Act: -0.1700

Data Index: 1144244 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 3.8140. Min Range: -3.8140

Max Act: 3.6575. Min Act: -0.1700

Data Index: 1188837 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 3.8140. Min Range: -3.8140

Max Act: 3.6888. Min Act: -0.1700

Data Index: 20872 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 3.8140. Min Range: -3.8140

Max Act: 3.6419. Min Act: -0.1700

Data Index: 859855 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 3.8140. Min Range: -3.8140

Max Act: 3.6575. Min Act: -0.1700

Data Index: 828092 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 3.8140. Min Range: -3.8140

Max Act: 3.6419. Min Act: -0.1700

Data Index: 182338 (C4 (Web Text))

Max Activating Token Index: 42

Text #19

Max Range: 3.8140. Min Range: -3.8140

Max Act: 3.6575. Min Act: -0.1700

Data Index: 644304 (C4 (Web Text))

Max Activating Token Index: 97