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

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

Neuron 1747 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4903. Min Range: -3.4903

Max Act: 3.4903. Min Act: -0.1700

Data Index: 328106 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 3.4903. Min Range: -3.4903

Max Act: 3.3963. Min Act: -0.1700

Data Index: 1123307 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.4903. Min Range: -3.4903

Max Act: 3.3178. Min Act: -0.1700

Data Index: 913273 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.4903. Min Range: -3.4903

Max Act: 3.3021. Min Act: -0.1700

Data Index: 1203162 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.4903. Min Range: -3.4903

Max Act: 3.1921. Min Act: -0.1700

Data Index: 1153170 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 3.4903. Min Range: -3.4903

Max Act: 3.1921. Min Act: -0.1700

Data Index: 1216488 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 3.4903. Min Range: -3.4903

Max Act: 3.1921. Min Act: -0.1700

Data Index: 961721 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 3.4903. Min Range: -3.4903

Max Act: 3.1921. Min Act: -0.1700

Data Index: 2950 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 3.4903. Min Range: -3.4903

Max Act: 3.1763. Min Act: -0.1700

Data Index: 1178901 (C4 (Web Text))

Max Activating Token Index: 11

Text #9

Max Range: 3.4903. Min Range: -3.4903

Max Act: 3.1763. Min Act: -0.1700

Data Index: 845423 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 3.4903. Min Range: -3.4903

Max Act: 3.1763. Min Act: -0.1700

Data Index: 103827 (C4 (Web Text))

Max Activating Token Index: 999

Text #11

Max Range: 3.4903. Min Range: -3.4903

Max Act: 3.1606. Min Act: -0.1700

Data Index: 1358847 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 3.4903. Min Range: -3.4903

Max Act: 3.1606. Min Act: -0.1700

Data Index: 1317819 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 3.4903. Min Range: -3.4903

Max Act: 3.1606. Min Act: -0.1700

Data Index: 27958 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 3.4903. Min Range: -3.4903

Max Act: 3.1448. Min Act: -0.1700

Data Index: 1292377 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 3.4903. Min Range: -3.4903

Max Act: 3.1606. Min Act: -0.1700

Data Index: 1234994 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 3.4903. Min Range: -3.4903

Max Act: 3.1448. Min Act: -0.1700

Data Index: 78507 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 3.4903. Min Range: -3.4903

Max Act: 3.1606. Min Act: -0.1700

Data Index: 979698 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 3.4903. Min Range: -3.4903

Max Act: 3.1448. Min Act: -0.1700

Data Index: 220332 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 3.4903. Min Range: -3.4903

Max Act: 3.1448. Min Act: -0.1700

Data Index: 1040123 (C4 (Web Text))

Max Activating Token Index: 831