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

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

Neuron 455 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.8778. Min Act: -0.1700

Data Index: 976482 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.8465. Min Act: -0.1700

Data Index: 1065786 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.7840. Min Act: -0.1700

Data Index: 1058271 (C4 (Web Text))

Max Activating Token Index: 430

Text #3

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.8153. Min Act: -0.1700

Data Index: 1240188 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.7527. Min Act: -0.1700

Data Index: 171495 (C4 (Web Text))

Max Activating Token Index: 935

Text #5

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.7840. Min Act: -0.1700

Data Index: 1105326 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.7214. Min Act: -0.1700

Data Index: 653173 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.8153. Min Act: -0.1700

Data Index: 1044012 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.7527. Min Act: -0.1700

Data Index: 1257843 (C4 (Web Text))

Max Activating Token Index: 346

Text #9

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.7527. Min Act: -0.1700

Data Index: 893949 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.7214. Min Act: -0.1700

Data Index: 655996 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.7527. Min Act: -0.1700

Data Index: 1070183 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.7527. Min Act: -0.1700

Data Index: 693904 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.7527. Min Act: -0.1700

Data Index: 301954 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.7840. Min Act: -0.1700

Data Index: 660123 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.7214. Min Act: -0.1700

Data Index: 361463 (C4 (Web Text))

Max Activating Token Index: 718

Text #16

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.7840. Min Act: -0.1700

Data Index: 111388 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.7527. Min Act: -0.1700

Data Index: 112539 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.7527. Min Act: -0.1700

Data Index: 58532 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 3.8778. Min Range: -3.8778

Max Act: 3.7527. Min Act: -0.1700

Data Index: 221853 (C4 (Web Text))

Max Activating Token Index: 449