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

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

Neuron 560 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: 920425 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.3421. Min Act: -0.1692

Data Index: 797477 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.2483. Min Act: -0.1699

Data Index: 516072 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.2171. Min Act: -0.1700

Data Index: 1291356 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.2171. Min Act: -0.1698

Data Index: 1068063 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.2171. Min Act: -0.1698

Data Index: 1270520 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.1858. Min Act: -0.1699

Data Index: 1282960 (C4 (Web Text))

Max Activating Token Index: 758

Text #7

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.1858. Min Act: -0.1690

Data Index: 1261827 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.0921. Min Act: -0.1700

Data Index: 1318370 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.1233. Min Act: -0.1700

Data Index: 1147492 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.1858. Min Act: -0.1700

Data Index: 678192 (C4 (Web Text))

Max Activating Token Index: 31

Text #11

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.1546. Min Act: -0.1700

Data Index: 729584 (C4 (Web Text))

Max Activating Token Index: 796

Text #12

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.0921. Min Act: -0.1700

Data Index: 1213300 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.0921. Min Act: -0.1699

Data Index: 141388 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.0608. Min Act: -0.1699

Data Index: 758356 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.0608. Min Act: -0.1700

Data Index: 171793 (C4 (Web Text))

Max Activating Token Index: 248

Text #16

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.0296. Min Act: -0.1700

Data Index: 1302040 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.0608. Min Act: -0.1692

Data Index: 1113560 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.0608. Min Act: -0.1700

Data Index: 381193 (C4 (Web Text))

Max Activating Token Index: 629

Text #19

Max Range: 5.4358. Min Range: -5.4358

Max Act: 5.0921. Min Act: -0.1700

Data Index: 103044 (C4 (Web Text))

Max Activating Token Index: 583