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

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

Neuron 1499 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3104. Min Range: -3.3104

Max Act: 3.3104. Min Act: -0.1700

Data Index: 916013 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 3.3104. Min Range: -3.3104

Max Act: 3.1846. Min Act: -0.1700

Data Index: 572769 (C4 (Web Text))

Max Activating Token Index: 638

Text #2

Max Range: 3.3104. Min Range: -3.3104

Max Act: 3.0901. Min Act: -0.1700

Data Index: 932938 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 3.3104. Min Range: -3.3104

Max Act: 3.0901. Min Act: -0.1700

Data Index: 1012860 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.3104. Min Range: -3.3104

Max Act: 3.0743. Min Act: -0.1700

Data Index: 1281426 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 3.3104. Min Range: -3.3104

Max Act: 3.0743. Min Act: -0.1700

Data Index: 13365 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 3.3104. Min Range: -3.3104

Max Act: 3.0743. Min Act: -0.1700

Data Index: 771368 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 3.3104. Min Range: -3.3104

Max Act: 3.0428. Min Act: -0.1700

Data Index: 446843 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 3.3104. Min Range: -3.3104

Max Act: 3.0743. Min Act: -0.1700

Data Index: 111695 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 3.3104. Min Range: -3.3104

Max Act: 3.0270. Min Act: -0.1700

Data Index: 45353 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.3104. Min Range: -3.3104

Max Act: 3.0428. Min Act: -0.1700

Data Index: 676464 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 3.3104. Min Range: -3.3104

Max Act: 3.0270. Min Act: -0.1700

Data Index: 334277 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 3.3104. Min Range: -3.3104

Max Act: 3.0270. Min Act: -0.1700

Data Index: 569694 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 3.3104. Min Range: -3.3104

Max Act: 3.0270. Min Act: -0.1700

Data Index: 803932 (C4 (Web Text))

Max Activating Token Index: 104

Text #14

Max Range: 3.3104. Min Range: -3.3104

Max Act: 3.0112. Min Act: -0.1700

Data Index: 996075 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 3.3104. Min Range: -3.3104

Max Act: 3.0270. Min Act: -0.1700

Data Index: 688918 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 3.3104. Min Range: -3.3104

Max Act: 2.9954. Min Act: -0.1700

Data Index: 397209 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 3.3104. Min Range: -3.3104

Max Act: 3.0112. Min Act: -0.1700

Data Index: 124886 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 3.3104. Min Range: -3.3104

Max Act: 2.9795. Min Act: -0.1700

Data Index: 924440 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 3.3104. Min Range: -3.3104

Max Act: 2.9954. Min Act: -0.1700

Data Index: 523076 (C4 (Web Text))

Max Activating Token Index: 1023