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

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

Neuron 53 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: 3.7803. Min Range: -3.7803

Max Act: 3.7803. Min Act: -0.1700

Data Index: 871751 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 3.7803. Min Range: -3.7803

Max Act: 3.7177. Min Act: -0.1700

Data Index: 150708 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 3.7803. Min Range: -3.7803

Max Act: 3.7333. Min Act: -0.1692

Data Index: 625072 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 3.7803. Min Range: -3.7803

Max Act: 3.7020. Min Act: -0.1700

Data Index: 624123 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 3.7803. Min Range: -3.7803

Max Act: 3.6707. Min Act: -0.1700

Data Index: 100437 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 3.7803. Min Range: -3.7803

Max Act: 3.6707. Min Act: -0.1700

Data Index: 211116 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 3.7803. Min Range: -3.7803

Max Act: 3.6394. Min Act: -0.1617

Data Index: 1194708 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 3.7803. Min Range: -3.7803

Max Act: 3.6707. Min Act: -0.1533

Data Index: 1229737 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 3.7803. Min Range: -3.7803

Max Act: 3.6864. Min Act: -0.1672

Data Index: 521788 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 3.7803. Min Range: -3.7803

Max Act: 3.6238. Min Act: -0.1538

Data Index: 153327 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 3.7803. Min Range: -3.7803

Max Act: 3.6238. Min Act: -0.1669

Data Index: 927089 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 3.7803. Min Range: -3.7803

Max Act: 3.5611. Min Act: -0.1679

Data Index: 680258 (C4 (Web Text))

Max Activating Token Index: 87

Text #12

Max Range: 3.7803. Min Range: -3.7803

Max Act: 3.5768. Min Act: -0.1697

Data Index: 1019415 (C4 (Web Text))

Max Activating Token Index: 115

Text #13

Max Range: 3.7803. Min Range: -3.7803

Max Act: 3.5768. Min Act: -0.1700

Data Index: 43816 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 3.7803. Min Range: -3.7803

Max Act: 3.5768. Min Act: -0.1700

Data Index: 577433 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 3.7803. Min Range: -3.7803

Max Act: 3.5455. Min Act: -0.1700

Data Index: 1011262 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 3.7803. Min Range: -3.7803

Max Act: 3.5768. Min Act: -0.1700

Data Index: 277793 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 3.7803. Min Range: -3.7803

Max Act: 3.5611. Min Act: -0.1693

Data Index: 444559 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 3.7803. Min Range: -3.7803

Max Act: 3.5298. Min Act: -0.1700

Data Index: 1164070 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 3.7803. Min Range: -3.7803

Max Act: 3.5455. Min Act: -0.1673

Data Index: 26088 (C4 (Web Text))

Max Activating Token Index: 86