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

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

Neuron 1700 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: 5.3247. Min Range: -5.3247

Max Act: 5.3247. Min Act: -0.1700

Data Index: 808779 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.1684. Min Act: -0.1700

Data Index: 871724 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.1997. Min Act: -0.1700

Data Index: 243579 (C4 (Web Text))

Max Activating Token Index: 1006

Text #3

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.1059. Min Act: -0.1700

Data Index: 450677 (C4 (Web Text))

Max Activating Token Index: 968

Text #4

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.1372. Min Act: -0.1700

Data Index: 849129 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.1372. Min Act: -0.1700

Data Index: 1150808 (C4 (Web Text))

Max Activating Token Index: 860

Text #6

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.0747. Min Act: -0.1700

Data Index: 883730 (C4 (Web Text))

Max Activating Token Index: 710

Text #7

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.0747. Min Act: -0.1700

Data Index: 234397 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.0747. Min Act: -0.1700

Data Index: 903063 (C4 (Web Text))

Max Activating Token Index: 940

Text #9

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.0434. Min Act: -0.1700

Data Index: 920654 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.0747. Min Act: -0.1700

Data Index: 795714 (C4 (Web Text))

Max Activating Token Index: 329

Text #11

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.0122. Min Act: -0.1700

Data Index: 1079976 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 5.3247. Min Range: -5.3247

Max Act: 4.9809. Min Act: -0.1700

Data Index: 403390 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 5.3247. Min Range: -5.3247

Max Act: 4.9497. Min Act: -0.1700

Data Index: 804504 (C4 (Web Text))

Max Activating Token Index: 450

Text #14

Max Range: 5.3247. Min Range: -5.3247

Max Act: 5.0122. Min Act: -0.1700

Data Index: 1004139 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 5.3247. Min Range: -5.3247

Max Act: 4.9497. Min Act: -0.1700

Data Index: 658165 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 5.3247. Min Range: -5.3247

Max Act: 4.9497. Min Act: -0.1700

Data Index: 1020911 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 5.3247. Min Range: -5.3247

Max Act: 4.9184. Min Act: -0.1700

Data Index: 845917 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 5.3247. Min Range: -5.3247

Max Act: 4.9184. Min Act: -0.1700

Data Index: 1082564 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 5.3247. Min Range: -5.3247

Max Act: 4.8872. Min Act: -0.1700

Data Index: 1184486 (C4 (Web Text))

Max Activating Token Index: 973