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

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

Neuron 1774 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: 5.8652. Min Range: -5.8652

Max Act: 5.8652. Min Act: -0.1700

Data Index: 906885 (C4 (Web Text))

Max Activating Token Index: 687

Text #1

Max Range: 5.8652. Min Range: -5.8652

Max Act: 5.7090. Min Act: -0.1700

Data Index: 1253986 (C4 (Web Text))

Max Activating Token Index: 829

Text #2

Max Range: 5.8652. Min Range: -5.8652

Max Act: 5.6465. Min Act: -0.1700

Data Index: 870454 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 5.8652. Min Range: -5.8652

Max Act: 5.3027. Min Act: -0.1700

Data Index: 767297 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 5.8652. Min Range: -5.8652

Max Act: 5.3027. Min Act: -0.1700

Data Index: 752928 (C4 (Web Text))

Max Activating Token Index: 937

Text #5

Max Range: 5.8652. Min Range: -5.8652

Max Act: 5.3027. Min Act: -0.1700

Data Index: 116853 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 5.8652. Min Range: -5.8652

Max Act: 5.3027. Min Act: -0.1699

Data Index: 330008 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 5.8652. Min Range: -5.8652

Max Act: 5.2715. Min Act: -0.1696

Data Index: 609593 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 5.8652. Min Range: -5.8652

Max Act: 5.2715. Min Act: -0.1700

Data Index: 249123 (C4 (Web Text))

Max Activating Token Index: 21

Text #9

Max Range: 5.8652. Min Range: -5.8652

Max Act: 5.2715. Min Act: -0.1700

Data Index: 534942 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 5.8652. Min Range: -5.8652

Max Act: 5.2090. Min Act: -0.1700

Data Index: 1185592 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 5.8652. Min Range: -5.8652

Max Act: 5.1465. Min Act: -0.1700

Data Index: 683519 (C4 (Web Text))

Max Activating Token Index: 820

Text #12

Max Range: 5.8652. Min Range: -5.8652

Max Act: 5.1777. Min Act: -0.1700

Data Index: 732971 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 5.8652. Min Range: -5.8652

Max Act: 5.1777. Min Act: -0.1700

Data Index: 997373 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 5.8652. Min Range: -5.8652

Max Act: 5.1152. Min Act: -0.1700

Data Index: 30346 (C4 (Web Text))

Max Activating Token Index: 140

Text #15

Max Range: 5.8652. Min Range: -5.8652

Max Act: 5.1465. Min Act: -0.1700

Data Index: 559228 (C4 (Web Text))

Max Activating Token Index: 444

Text #16

Max Range: 5.8652. Min Range: -5.8652

Max Act: 5.1465. Min Act: -0.1700

Data Index: 585544 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 5.8652. Min Range: -5.8652

Max Act: 5.1465. Min Act: -0.1700

Data Index: 457444 (C4 (Web Text))

Max Activating Token Index: 396

Text #18

Max Range: 5.8652. Min Range: -5.8652

Max Act: 5.0840. Min Act: -0.1700

Data Index: 810481 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 5.8652. Min Range: -5.8652

Max Act: 5.0527. Min Act: -0.1700

Data Index: 363528 (C4 (Web Text))

Max Activating Token Index: 646