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

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

Neuron 1692 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.4358. Min Act: -0.1700

Data Index: 347092 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.2170. Min Act: -0.1700

Data Index: 765522 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.0295. Min Act: -0.1700

Data Index: 104158 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.0608. Min Act: -0.1700

Data Index: 145341 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.0608. Min Act: -0.1700

Data Index: 960330 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.0920. Min Act: -0.1700

Data Index: 73397 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.0608. Min Act: -0.1700

Data Index: 561486 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 5.4358. Min Range: -5.4358

Max Act: 4.9983. Min Act: -0.1700

Data Index: 19872 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 5.4358. Min Range: -5.4358

Max Act: 4.9670. Min Act: -0.1700

Data Index: 470395 (C4 (Web Text))

Max Activating Token Index: 248

Text #9

Max Range: 5.4358. Min Range: -5.4358

Max Act: 4.9358. Min Act: -0.1700

Data Index: 967464 (C4 (Web Text))

Max Activating Token Index: 296

Text #10

Max Range: 5.4358. Min Range: -5.4358

Max Act: 4.9358. Min Act: -0.1700

Data Index: 154302 (C4 (Web Text))

Max Activating Token Index: 232

Text #11

Max Range: 5.4358. Min Range: -5.4358

Max Act: 4.9358. Min Act: -0.1700

Data Index: 197863 (C4 (Web Text))

Max Activating Token Index: 1022

Text #12

Max Range: 5.4358. Min Range: -5.4358

Max Act: 4.9670. Min Act: -0.1700

Data Index: 318333 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 5.4358. Min Range: -5.4358

Max Act: 4.9670. Min Act: -0.1700

Data Index: 706036 (C4 (Web Text))

Max Activating Token Index: 685

Text #14

Max Range: 5.4358. Min Range: -5.4358

Max Act: 4.9983. Min Act: -0.1700

Data Index: 759873 (C4 (Web Text))

Max Activating Token Index: 736

Text #15

Max Range: 5.4358. Min Range: -5.4358

Max Act: 4.9045. Min Act: -0.1700

Data Index: 355902 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 5.4358. Min Range: -5.4358

Max Act: 4.9045. Min Act: -0.1700

Data Index: 1352727 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 5.4358. Min Range: -5.4358

Max Act: 4.9045. Min Act: -0.1700

Data Index: 1174896 (C4 (Web Text))

Max Activating Token Index: 465

Text #18

Max Range: 5.4358. Min Range: -5.4358

Max Act: 4.8733. Min Act: -0.1700

Data Index: 973919 (C4 (Web Text))

Max Activating Token Index: 366

Text #19

Max Range: 5.4358. Min Range: -5.4358

Max Act: 4.8733. Min Act: -0.1700

Data Index: 389593 (C4 (Web Text))

Max Activating Token Index: 784