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

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

Neuron 847 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: 5.4145. Min Range: -5.4145

Max Act: 5.4145. Min Act: -0.1700

Data Index: 60178 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 5.4145. Min Range: -5.4145

Max Act: 5.3520. Min Act: -0.1700

Data Index: 1089754 (C4 (Web Text))

Max Activating Token Index: 690

Text #2

Max Range: 5.4145. Min Range: -5.4145

Max Act: 5.3520. Min Act: -0.1700

Data Index: 701579 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 5.4145. Min Range: -5.4145

Max Act: 5.4145. Min Act: -0.1700

Data Index: 1193076 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 5.4145. Min Range: -5.4145

Max Act: 5.3520. Min Act: -0.1700

Data Index: 377176 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 5.4145. Min Range: -5.4145

Max Act: 5.2895. Min Act: -0.1700

Data Index: 168839 (C4 (Web Text))

Max Activating Token Index: 881

Text #6

Max Range: 5.4145. Min Range: -5.4145

Max Act: 5.2895. Min Act: -0.1700

Data Index: 798861 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 5.4145. Min Range: -5.4145

Max Act: 5.2895. Min Act: -0.1700

Data Index: 255357 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 5.4145. Min Range: -5.4145

Max Act: 5.2895. Min Act: -0.1700

Data Index: 1181228 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 5.4145. Min Range: -5.4145

Max Act: 5.2895. Min Act: -0.1700

Data Index: 999855 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 5.4145. Min Range: -5.4145

Max Act: 5.2270. Min Act: -0.1700

Data Index: 139872 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 5.4145. Min Range: -5.4145

Max Act: 5.2895. Min Act: -0.1700

Data Index: 658793 (C4 (Web Text))

Max Activating Token Index: 871

Text #12

Max Range: 5.4145. Min Range: -5.4145

Max Act: 5.2270. Min Act: -0.1700

Data Index: 1087062 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 5.4145. Min Range: -5.4145

Max Act: 5.2895. Min Act: -0.1700

Data Index: 49738 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 5.4145. Min Range: -5.4145

Max Act: 5.2270. Min Act: -0.1700

Data Index: 1430434 (Python Code)

Max Activating Token Index: 418

Text #15

Max Range: 5.4145. Min Range: -5.4145

Max Act: 5.1645. Min Act: -0.1700

Data Index: 1079404 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 5.4145. Min Range: -5.4145

Max Act: 5.1645. Min Act: -0.1700

Data Index: 631198 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 5.4145. Min Range: -5.4145

Max Act: 5.1645. Min Act: -0.1700

Data Index: 756053 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 5.4145. Min Range: -5.4145

Max Act: 5.1645. Min Act: -0.1700

Data Index: 696687 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 5.4145. Min Range: -5.4145

Max Act: 5.1020. Min Act: -0.1700

Data Index: 503478 (C4 (Web Text))

Max Activating Token Index: 182