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

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

Neuron 1014 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: 3.2807. Min Range: -3.2807

Max Act: 3.2807. Min Act: -0.1700

Data Index: 639473 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.1234. Min Act: -0.1700

Data Index: 223575 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.1234. Min Act: -0.1700

Data Index: 1314816 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0919. Min Act: -0.1700

Data Index: 1213313 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.1076. Min Act: -0.1700

Data Index: 1133850 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0919. Min Act: -0.1700

Data Index: 827982 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0919. Min Act: -0.1700

Data Index: 1082489 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0761. Min Act: -0.1700

Data Index: 1180484 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0919. Min Act: -0.1700

Data Index: 1143250 (C4 (Web Text))

Max Activating Token Index: 252

Text #9

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0919. Min Act: -0.1700

Data Index: 963625 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0919. Min Act: -0.1700

Data Index: 980044 (C4 (Web Text))

Max Activating Token Index: 190

Text #11

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0603. Min Act: -0.1700

Data Index: 1255774 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0761. Min Act: -0.1700

Data Index: 435723 (C4 (Web Text))

Max Activating Token Index: 254

Text #13

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0919. Min Act: -0.1700

Data Index: 573239 (C4 (Web Text))

Max Activating Token Index: 709

Text #14

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0919. Min Act: -0.1700

Data Index: 150322 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0603. Min Act: -0.1700

Data Index: 87224 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0603. Min Act: -0.1700

Data Index: 453273 (C4 (Web Text))

Max Activating Token Index: 997

Text #17

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0603. Min Act: -0.1700

Data Index: 986749 (C4 (Web Text))

Max Activating Token Index: 670

Text #18

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0603. Min Act: -0.1700

Data Index: 275506 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 3.2807. Min Range: -3.2807

Max Act: 3.0603. Min Act: -0.1700

Data Index: 337338 (C4 (Web Text))

Max Activating Token Index: 608