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

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

Neuron 635 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.7284. Min Act: -0.1700

Data Index: 1333533 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.6189. Min Act: -0.1700

Data Index: 1039913 (C4 (Web Text))

Max Activating Token Index: 585

Text #2

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.6189. Min Act: -0.1700

Data Index: 670739 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.5562. Min Act: -0.1700

Data Index: 942139 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.5719. Min Act: -0.1700

Data Index: 183829 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.5562. Min Act: -0.1700

Data Index: 273070 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.4936. Min Act: -0.1700

Data Index: 1216952 (C4 (Web Text))

Max Activating Token Index: 727

Text #7

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.4465. Min Act: -0.1700

Data Index: 923537 (C4 (Web Text))

Max Activating Token Index: 62

Text #8

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.4622. Min Act: -0.1700

Data Index: 12486 (C4 (Web Text))

Max Activating Token Index: 705

Text #9

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.4465. Min Act: -0.1700

Data Index: 1293046 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.4779. Min Act: -0.1700

Data Index: 685270 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.4779. Min Act: -0.1700

Data Index: 690921 (C4 (Web Text))

Max Activating Token Index: 987

Text #12

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.4152. Min Act: -0.1700

Data Index: 444801 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.4465. Min Act: -0.1700

Data Index: 436772 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.4465. Min Act: -0.1700

Data Index: 1171470 (C4 (Web Text))

Max Activating Token Index: 339

Text #15

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.4152. Min Act: -0.1700

Data Index: 504091 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.3995. Min Act: -0.1700

Data Index: 1049314 (C4 (Web Text))

Max Activating Token Index: 335

Text #17

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.3995. Min Act: -0.1700

Data Index: 291462 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.3838. Min Act: -0.1700

Data Index: 820887 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 3.7284. Min Range: -3.7284

Max Act: 3.3838. Min Act: -0.1700

Data Index: 292107 (C4 (Web Text))

Max Activating Token Index: 195