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

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

Neuron 1051 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: 7.8454. Min Range: -7.8454

Max Act: 7.8454. Min Act: -0.1697

Data Index: 49433 (C4 (Web Text))

Max Activating Token Index: 673

Text #1

Max Range: 7.8454. Min Range: -7.8454

Max Act: 7.5954. Min Act: -0.1699

Data Index: 1202521 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 7.8454. Min Range: -7.8454

Max Act: 7.5641. Min Act: -0.1700

Data Index: 16475 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 7.8454. Min Range: -7.8454

Max Act: 7.5329. Min Act: -0.1699

Data Index: 1198913 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 7.8454. Min Range: -7.8454

Max Act: 7.5016. Min Act: -0.1698

Data Index: 202012 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 7.8454. Min Range: -7.8454

Max Act: 7.4391. Min Act: -0.1700

Data Index: 217223 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 7.8454. Min Range: -7.8454

Max Act: 7.4079. Min Act: -0.1700

Data Index: 547384 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 7.8454. Min Range: -7.8454

Max Act: 7.4079. Min Act: -0.1700

Data Index: 970304 (C4 (Web Text))

Max Activating Token Index: 757

Text #8

Max Range: 7.8454. Min Range: -7.8454

Max Act: 7.3141. Min Act: -0.1697

Data Index: 1332345 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 7.8454. Min Range: -7.8454

Max Act: 7.3141. Min Act: -0.1694

Data Index: 701199 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 7.8454. Min Range: -7.8454

Max Act: 7.2829. Min Act: -0.1700

Data Index: 618476 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 7.8454. Min Range: -7.8454

Max Act: 7.2829. Min Act: -0.1699

Data Index: 389923 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 7.8454. Min Range: -7.8454

Max Act: 7.2829. Min Act: -0.1699

Data Index: 649122 (C4 (Web Text))

Max Activating Token Index: 221

Text #13

Max Range: 7.8454. Min Range: -7.8454

Max Act: 7.2829. Min Act: -0.1700

Data Index: 1284175 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 7.8454. Min Range: -7.8454

Max Act: 7.2516. Min Act: -0.1700

Data Index: 78490 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 7.8454. Min Range: -7.8454

Max Act: 7.2516. Min Act: -0.1700

Data Index: 1236082 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 7.8454. Min Range: -7.8454

Max Act: 7.2204. Min Act: -0.1700

Data Index: 435246 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 7.8454. Min Range: -7.8454

Max Act: 7.1891. Min Act: -0.1700

Data Index: 1280891 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 7.8454. Min Range: -7.8454

Max Act: 7.1579. Min Act: -0.1699

Data Index: 354860 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 7.8454. Min Range: -7.8454

Max Act: 7.1891. Min Act: -0.1699

Data Index: 531403 (C4 (Web Text))

Max Activating Token Index: 943