Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1753 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.2902. Min Range: -3.2902

Max Act: 3.2902. Min Act: -0.1696

Data Index: 565391 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 3.2902. Min Range: -3.2902

Max Act: 3.1958. Min Act: -0.1694

Data Index: 1311753 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 3.2902. Min Range: -3.2902

Max Act: 3.1801. Min Act: -0.1591

Data Index: 1098606 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 3.2902. Min Range: -3.2902

Max Act: 3.1644. Min Act: -0.1700

Data Index: 1151501 (C4 (Web Text))

Max Activating Token Index: 727

Text #4

Max Range: 3.2902. Min Range: -3.2902

Max Act: 3.1644. Min Act: -0.1697

Data Index: 1174344 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 3.2902. Min Range: -3.2902

Max Act: 3.1486. Min Act: -0.1697

Data Index: 1326609 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 3.2902. Min Range: -3.2902

Max Act: 3.1486. Min Act: -0.1699

Data Index: 757800 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 3.2902. Min Range: -3.2902

Max Act: 3.1486. Min Act: -0.1639

Data Index: 1127887 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 3.2902. Min Range: -3.2902

Max Act: 3.1329. Min Act: -0.1699

Data Index: 927035 (C4 (Web Text))

Max Activating Token Index: 911

Text #9

Max Range: 3.2902. Min Range: -3.2902

Max Act: 3.1329. Min Act: -0.1700

Data Index: 1044909 (C4 (Web Text))

Max Activating Token Index: 733

Text #10

Max Range: 3.2902. Min Range: -3.2902

Max Act: 3.1329. Min Act: -0.1696

Data Index: 313234 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 3.2902. Min Range: -3.2902

Max Act: 3.1329. Min Act: -0.1700

Data Index: 152100 (C4 (Web Text))

Max Activating Token Index: 719

Text #12

Max Range: 3.2902. Min Range: -3.2902

Max Act: 3.1171. Min Act: -0.1695

Data Index: 1223899 (C4 (Web Text))

Max Activating Token Index: 758

Text #13

Max Range: 3.2902. Min Range: -3.2902

Max Act: 3.1171. Min Act: -0.1700

Data Index: 650083 (C4 (Web Text))

Max Activating Token Index: 242

Text #14

Max Range: 3.2902. Min Range: -3.2902

Max Act: 3.1013. Min Act: -0.1700

Data Index: 1353253 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 3.2902. Min Range: -3.2902

Max Act: 3.1171. Min Act: -0.1698

Data Index: 463286 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 3.2902. Min Range: -3.2902

Max Act: 3.1171. Min Act: -0.1699

Data Index: 728423 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 3.2902. Min Range: -3.2902

Max Act: 3.1013. Min Act: -0.1696

Data Index: 707430 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 3.2902. Min Range: -3.2902

Max Act: 3.1013. Min Act: -0.1699

Data Index: 182437 (C4 (Web Text))

Max Activating Token Index: 171

Text #19

Max Range: 3.2902. Min Range: -3.2902

Max Act: 3.1171. Min Act: -0.1696

Data Index: 631336 (C4 (Web Text))

Max Activating Token Index: 320