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

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

Neuron 586 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: 5.1211. Min Range: -5.1211

Max Act: 5.1211. Min Act: -0.1700

Data Index: 273898 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 5.1211. Min Range: -5.1211

Max Act: 5.0898. Min Act: -0.1700

Data Index: 688781 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 5.1211. Min Range: -5.1211

Max Act: 5.0273. Min Act: -0.1700

Data Index: 634917 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 5.1211. Min Range: -5.1211

Max Act: 4.9335. Min Act: -0.1700

Data Index: 1250184 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 5.1211. Min Range: -5.1211

Max Act: 4.9023. Min Act: -0.1700

Data Index: 1091115 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 5.1211. Min Range: -5.1211

Max Act: 4.8710. Min Act: -0.1700

Data Index: 1009655 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 5.1211. Min Range: -5.1211

Max Act: 4.8398. Min Act: -0.1700

Data Index: 60522 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 5.1211. Min Range: -5.1211

Max Act: 4.7773. Min Act: -0.1700

Data Index: 1338570 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 5.1211. Min Range: -5.1211

Max Act: 4.7460. Min Act: -0.1700

Data Index: 616070 (C4 (Web Text))

Max Activating Token Index: 996

Text #9

Max Range: 5.1211. Min Range: -5.1211

Max Act: 4.7460. Min Act: -0.1700

Data Index: 827894 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 5.1211. Min Range: -5.1211

Max Act: 4.7773. Min Act: -0.1700

Data Index: 372956 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 5.1211. Min Range: -5.1211

Max Act: 4.7460. Min Act: -0.1700

Data Index: 1246741 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 5.1211. Min Range: -5.1211

Max Act: 4.7773. Min Act: -0.1700

Data Index: 199281 (C4 (Web Text))

Max Activating Token Index: 855

Text #13

Max Range: 5.1211. Min Range: -5.1211

Max Act: 4.6523. Min Act: -0.1700

Data Index: 758085 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 5.1211. Min Range: -5.1211

Max Act: 4.6835. Min Act: -0.1700

Data Index: 356863 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 5.1211. Min Range: -5.1211

Max Act: 4.5898. Min Act: -0.1700

Data Index: 486997 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 5.1211. Min Range: -5.1211

Max Act: 4.6523. Min Act: -0.1700

Data Index: 167520 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 5.1211. Min Range: -5.1211

Max Act: 4.6835. Min Act: -0.1700

Data Index: 547921 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 5.1211. Min Range: -5.1211

Max Act: 4.5898. Min Act: -0.1700

Data Index: 750784 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 5.1211. Min Range: -5.1211

Max Act: 4.5898. Min Act: -0.1700

Data Index: 997093 (C4 (Web Text))

Max Activating Token Index: 839