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

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

Neuron 562 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.2794. Min Act: -0.1700

Data Index: 331741 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.1851. Min Act: -0.1700

Data Index: 888812 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.1378. Min Act: -0.1700

Data Index: 1119936 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.1221. Min Act: -0.1700

Data Index: 383499 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.1063. Min Act: -0.1700

Data Index: 1030428 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.1063. Min Act: -0.1700

Data Index: 149047 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.1063. Min Act: -0.1700

Data Index: 1233945 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.0748. Min Act: -0.1700

Data Index: 634433 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.0748. Min Act: -0.1700

Data Index: 596423 (C4 (Web Text))

Max Activating Token Index: 772

Text #9

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.0748. Min Act: -0.1700

Data Index: 486204 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.0590. Min Act: -0.1700

Data Index: 810573 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.0432. Min Act: -0.1700

Data Index: 152443 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.0432. Min Act: -0.1700

Data Index: 1048737 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.0274. Min Act: -0.1700

Data Index: 464251 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.0274. Min Act: -0.1700

Data Index: 789241 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.0432. Min Act: -0.1700

Data Index: 382292 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.0590. Min Act: -0.1700

Data Index: 573110 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.0274. Min Act: -0.1700

Data Index: 803208 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.0274. Min Act: -0.1700

Data Index: 841914 (C4 (Web Text))

Max Activating Token Index: 95

Text #19

Max Range: 3.2794. Min Range: -3.2794

Max Act: 3.0274. Min Act: -0.1700

Data Index: 202055 (C4 (Web Text))

Max Activating Token Index: 492