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

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

Neuron 739 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1776. Min Range: -5.1776

Max Act: 5.1776. Min Act: -0.1700

Data Index: 23489 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 5.1776. Min Range: -5.1776

Max Act: 5.0526. Min Act: -0.1700

Data Index: 44335 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 5.1776. Min Range: -5.1776

Max Act: 5.0839. Min Act: -0.1700

Data Index: 1086721 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 5.1776. Min Range: -5.1776

Max Act: 5.1464. Min Act: -0.1700

Data Index: 1065653 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 5.1776. Min Range: -5.1776

Max Act: 5.1464. Min Act: -0.1700

Data Index: 1137260 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 5.1776. Min Range: -5.1776

Max Act: 5.0526. Min Act: -0.1700

Data Index: 836054 (C4 (Web Text))

Max Activating Token Index: 1012

Text #6

Max Range: 5.1776. Min Range: -5.1776

Max Act: 5.0839. Min Act: -0.1700

Data Index: 781647 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 5.1776. Min Range: -5.1776

Max Act: 5.0526. Min Act: -0.1700

Data Index: 496895 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 5.1776. Min Range: -5.1776

Max Act: 5.0214. Min Act: -0.1700

Data Index: 110856 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 5.1776. Min Range: -5.1776

Max Act: 5.0526. Min Act: -0.1700

Data Index: 1135623 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 5.1776. Min Range: -5.1776

Max Act: 4.9901. Min Act: -0.1700

Data Index: 867265 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 5.1776. Min Range: -5.1776

Max Act: 5.0526. Min Act: -0.1700

Data Index: 1257437 (C4 (Web Text))

Max Activating Token Index: 627

Text #12

Max Range: 5.1776. Min Range: -5.1776

Max Act: 5.0214. Min Act: -0.1700

Data Index: 461222 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 5.1776. Min Range: -5.1776

Max Act: 5.0526. Min Act: -0.1700

Data Index: 503388 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 5.1776. Min Range: -5.1776

Max Act: 4.9589. Min Act: -0.1700

Data Index: 861423 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 5.1776. Min Range: -5.1776

Max Act: 4.9901. Min Act: -0.1700

Data Index: 744074 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 5.1776. Min Range: -5.1776

Max Act: 5.0214. Min Act: -0.1700

Data Index: 1225517 (C4 (Web Text))

Max Activating Token Index: 737

Text #17

Max Range: 5.1776. Min Range: -5.1776

Max Act: 4.9589. Min Act: -0.1700

Data Index: 437756 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 5.1776. Min Range: -5.1776

Max Act: 4.9276. Min Act: -0.1700

Data Index: 1025125 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 5.1776. Min Range: -5.1776

Max Act: 4.8964. Min Act: -0.1700

Data Index: 436436 (C4 (Web Text))

Max Activating Token Index: 460