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

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

Neuron 791 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: 5.3829. Min Range: -5.3829

Max Act: 5.3829. Min Act: -0.1700

Data Index: 795874 (C4 (Web Text))

Max Activating Token Index: 370

Text #1

Max Range: 5.3829. Min Range: -5.3829

Max Act: 5.3829. Min Act: -0.1700

Data Index: 602692 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 5.3829. Min Range: -5.3829

Max Act: 5.2579. Min Act: -0.1700

Data Index: 1286248 (C4 (Web Text))

Max Activating Token Index: 670

Text #3

Max Range: 5.3829. Min Range: -5.3829

Max Act: 5.2891. Min Act: -0.1699

Data Index: 1113560 (C4 (Web Text))

Max Activating Token Index: 286

Text #4

Max Range: 5.3829. Min Range: -5.3829

Max Act: 5.1954. Min Act: -0.1700

Data Index: 446639 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 5.3829. Min Range: -5.3829

Max Act: 5.1954. Min Act: -0.1700

Data Index: 222099 (C4 (Web Text))

Max Activating Token Index: 1011

Text #6

Max Range: 5.3829. Min Range: -5.3829

Max Act: 5.1641. Min Act: -0.1700

Data Index: 919725 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 5.3829. Min Range: -5.3829

Max Act: 5.1329. Min Act: -0.1700

Data Index: 945959 (C4 (Web Text))

Max Activating Token Index: 743

Text #8

Max Range: 5.3829. Min Range: -5.3829

Max Act: 5.1016. Min Act: -0.1700

Data Index: 1078202 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 5.3829. Min Range: -5.3829

Max Act: 5.0703. Min Act: -0.1700

Data Index: 708272 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 5.3829. Min Range: -5.3829

Max Act: 5.0078. Min Act: -0.1700

Data Index: 274611 (C4 (Web Text))

Max Activating Token Index: 397

Text #11

Max Range: 5.3829. Min Range: -5.3829

Max Act: 4.9141. Min Act: -0.1700

Data Index: 1086867 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 5.3829. Min Range: -5.3829

Max Act: 4.9453. Min Act: -0.1700

Data Index: 380877 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 5.3829. Min Range: -5.3829

Max Act: 4.9766. Min Act: -0.1700

Data Index: 175103 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 5.3829. Min Range: -5.3829

Max Act: 4.9453. Min Act: -0.1700

Data Index: 1031124 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 5.3829. Min Range: -5.3829

Max Act: 4.9453. Min Act: -0.1700

Data Index: 507538 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 5.3829. Min Range: -5.3829

Max Act: 4.9453. Min Act: -0.1700

Data Index: 722316 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 5.3829. Min Range: -5.3829

Max Act: 4.9141. Min Act: -0.1700

Data Index: 374491 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 5.3829. Min Range: -5.3829

Max Act: 4.9141. Min Act: -0.1700

Data Index: 734061 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 5.3829. Min Range: -5.3829

Max Act: 4.9141. Min Act: -0.1700

Data Index: 1262403 (C4 (Web Text))

Max Activating Token Index: 873