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

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

Neuron 219 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0537. Min Range: -5.0537

Max Act: 5.0537. Min Act: -0.1700

Data Index: 292042 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 5.0537. Min Range: -5.0537

Max Act: 4.9912. Min Act: -0.1700

Data Index: 54808 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 5.0537. Min Range: -5.0537

Max Act: 4.9599. Min Act: -0.1700

Data Index: 1501367 (Python Code)

Max Activating Token Index: 767

Text #3

Max Range: 5.0537. Min Range: -5.0537

Max Act: 4.9912. Min Act: -0.1700

Data Index: 1250194 (C4 (Web Text))

Max Activating Token Index: 123

Text #4

Max Range: 5.0537. Min Range: -5.0537

Max Act: 4.8662. Min Act: -0.1700

Data Index: 1262766 (C4 (Web Text))

Max Activating Token Index: 1010

Text #5

Max Range: 5.0537. Min Range: -5.0537

Max Act: 4.8037. Min Act: -0.1700

Data Index: 476462 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 5.0537. Min Range: -5.0537

Max Act: 4.8037. Min Act: -0.1700

Data Index: 836733 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 5.0537. Min Range: -5.0537

Max Act: 4.9287. Min Act: -0.1700

Data Index: 137973 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 5.0537. Min Range: -5.0537

Max Act: 4.8974. Min Act: -0.1700

Data Index: 1311822 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 5.0537. Min Range: -5.0537

Max Act: 4.7099. Min Act: -0.1700

Data Index: 674425 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 5.0537. Min Range: -5.0537

Max Act: 4.7724. Min Act: -0.1700

Data Index: 787678 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 5.0537. Min Range: -5.0537

Max Act: 4.8662. Min Act: -0.1700

Data Index: 1064278 (C4 (Web Text))

Max Activating Token Index: 692

Text #12

Max Range: 5.0537. Min Range: -5.0537

Max Act: 4.7724. Min Act: -0.1700

Data Index: 1402754 (Python Code)

Max Activating Token Index: 128

Text #13

Max Range: 5.0537. Min Range: -5.0537

Max Act: 4.7412. Min Act: -0.1700

Data Index: 1550139 (Python Code)

Max Activating Token Index: 1014

Text #14

Max Range: 5.0537. Min Range: -5.0537

Max Act: 4.8037. Min Act: -0.1700

Data Index: 1632143 (Python Code)

Max Activating Token Index: 829

Text #15

Max Range: 5.0537. Min Range: -5.0537

Max Act: 4.8037. Min Act: -0.1700

Data Index: 583444 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 5.0537. Min Range: -5.0537

Max Act: 4.7412. Min Act: -0.1700

Data Index: 865450 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 5.0537. Min Range: -5.0537

Max Act: 4.7724. Min Act: -0.1700

Data Index: 500659 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 5.0537. Min Range: -5.0537

Max Act: 4.8037. Min Act: -0.1700

Data Index: 132899 (C4 (Web Text))

Max Activating Token Index: 917

Text #19

Max Range: 5.0537. Min Range: -5.0537

Max Act: 4.8037. Min Act: -0.1700

Data Index: 1018165 (C4 (Web Text))

Max Activating Token Index: 112