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

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

Neuron 621 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.8501. Min Act: -0.1700

Data Index: 226595 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.7876. Min Act: -0.1700

Data Index: 383008 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.6311. Min Act: -0.1700

Data Index: 1257730 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5685. Min Act: -0.1700

Data Index: 607800 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5998. Min Act: -0.1700

Data Index: 1183870 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5998. Min Act: -0.1700

Data Index: 717272 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5998. Min Act: -0.1700

Data Index: 773819 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5998. Min Act: -0.1700

Data Index: 493921 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5685. Min Act: -0.1700

Data Index: 866858 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5685. Min Act: -0.1700

Data Index: 854854 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5998. Min Act: -0.1700

Data Index: 839965 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5685. Min Act: -0.1700

Data Index: 235118 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.6311. Min Act: -0.1700

Data Index: 930217 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5998. Min Act: -0.1700

Data Index: 252969 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5685. Min Act: -0.1700

Data Index: 183013 (C4 (Web Text))

Max Activating Token Index: 792

Text #15

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5685. Min Act: -0.1700

Data Index: 952283 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5372. Min Act: -0.1700

Data Index: 400689 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5685. Min Act: -0.1700

Data Index: 37043 (C4 (Web Text))

Max Activating Token Index: 534

Text #18

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5685. Min Act: -0.1700

Data Index: 414472 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 3.8501. Min Range: -3.8501

Max Act: 3.5372. Min Act: -0.1700

Data Index: 837342 (C4 (Web Text))

Max Activating Token Index: 498