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

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

Neuron 150 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3122. Min Range: -7.3122

Max Act: 7.3122. Min Act: -0.1700

Data Index: 1156375 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 7.3122. Min Range: -7.3122

Max Act: 6.9372. Min Act: -0.1700

Data Index: 298402 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 7.3122. Min Range: -7.3122

Max Act: 7.0622. Min Act: -0.1699

Data Index: 546445 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 7.3122. Min Range: -7.3122

Max Act: 6.8122. Min Act: -0.1700

Data Index: 574005 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 7.3122. Min Range: -7.3122

Max Act: 6.6872. Min Act: -0.1699

Data Index: 1154462 (C4 (Web Text))

Max Activating Token Index: 404

Text #5

Max Range: 7.3122. Min Range: -7.3122

Max Act: 6.6247. Min Act: -0.1697

Data Index: 1015308 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 7.3122. Min Range: -7.3122

Max Act: 6.6872. Min Act: -0.1699

Data Index: 228070 (C4 (Web Text))

Max Activating Token Index: 570

Text #7

Max Range: 7.3122. Min Range: -7.3122

Max Act: 6.7497. Min Act: -0.1700

Data Index: 1349639 (C4 (Web Text))

Max Activating Token Index: 674

Text #8

Max Range: 7.3122. Min Range: -7.3122

Max Act: 6.4997. Min Act: -0.1700

Data Index: 748344 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 7.3122. Min Range: -7.3122

Max Act: 6.6872. Min Act: -0.1698

Data Index: 635049 (C4 (Web Text))

Max Activating Token Index: 645

Text #10

Max Range: 7.3122. Min Range: -7.3122

Max Act: 6.4997. Min Act: -0.1695

Data Index: 239496 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 7.3122. Min Range: -7.3122

Max Act: 6.5622. Min Act: -0.1700

Data Index: 673025 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 7.3122. Min Range: -7.3122

Max Act: 6.6872. Min Act: -0.1699

Data Index: 1073668 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 7.3122. Min Range: -7.3122

Max Act: 6.5622. Min Act: -0.1700

Data Index: 338094 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 7.3122. Min Range: -7.3122

Max Act: 6.5622. Min Act: -0.1700

Data Index: 717766 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 7.3122. Min Range: -7.3122

Max Act: 6.5622. Min Act: -0.1700

Data Index: 725410 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 7.3122. Min Range: -7.3122

Max Act: 6.8122. Min Act: -0.1697

Data Index: 1300139 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 7.3122. Min Range: -7.3122

Max Act: 6.4997. Min Act: -0.1698

Data Index: 106148 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 7.3122. Min Range: -7.3122

Max Act: 6.5622. Min Act: -0.1700

Data Index: 740272 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 7.3122. Min Range: -7.3122

Max Act: 6.6872. Min Act: -0.1700

Data Index: 962295 (C4 (Web Text))

Max Activating Token Index: 647