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

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

Neuron 1492 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.5423. Min Range: -5.5423

Max Act: 5.4798. Min Act: -0.1700

Data Index: 1219551 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 5.5423. Min Range: -5.5423

Max Act: 5.5423. Min Act: -0.1700

Data Index: 845782 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 5.5423. Min Range: -5.5423

Max Act: 5.4486. Min Act: -0.1700

Data Index: 19563 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 5.5423. Min Range: -5.5423

Max Act: 5.3236. Min Act: -0.1700

Data Index: 1249971 (C4 (Web Text))

Max Activating Token Index: 678

Text #4

Max Range: 5.5423. Min Range: -5.5423

Max Act: 5.4173. Min Act: -0.1700

Data Index: 630894 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 5.5423. Min Range: -5.5423

Max Act: 5.4486. Min Act: -0.1700

Data Index: 976340 (C4 (Web Text))

Max Activating Token Index: 699

Text #6

Max Range: 5.5423. Min Range: -5.5423

Max Act: 5.3548. Min Act: -0.1700

Data Index: 1053280 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 5.5423. Min Range: -5.5423

Max Act: 5.3861. Min Act: -0.1700

Data Index: 43411 (C4 (Web Text))

Max Activating Token Index: 889

Text #8

Max Range: 5.5423. Min Range: -5.5423

Max Act: 5.2923. Min Act: -0.1700

Data Index: 209376 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 5.5423. Min Range: -5.5423

Max Act: 5.2923. Min Act: -0.1700

Data Index: 796237 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 5.5423. Min Range: -5.5423

Max Act: 5.3548. Min Act: -0.1700

Data Index: 478357 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 5.5423. Min Range: -5.5423

Max Act: 5.3548. Min Act: -0.1700

Data Index: 52620 (C4 (Web Text))

Max Activating Token Index: 202

Text #12

Max Range: 5.5423. Min Range: -5.5423

Max Act: 5.2611. Min Act: -0.1700

Data Index: 793844 (C4 (Web Text))

Max Activating Token Index: 650

Text #13

Max Range: 5.5423. Min Range: -5.5423

Max Act: 5.3548. Min Act: -0.1700

Data Index: 1232041 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 5.5423. Min Range: -5.5423

Max Act: 5.2298. Min Act: -0.1700

Data Index: 965934 (C4 (Web Text))

Max Activating Token Index: 822

Text #15

Max Range: 5.5423. Min Range: -5.5423

Max Act: 5.3236. Min Act: -0.1700

Data Index: 804005 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 5.5423. Min Range: -5.5423

Max Act: 5.2923. Min Act: -0.1700

Data Index: 1308381 (C4 (Web Text))

Max Activating Token Index: 155

Text #17

Max Range: 5.5423. Min Range: -5.5423

Max Act: 5.3548. Min Act: -0.1700

Data Index: 636866 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 5.5423. Min Range: -5.5423

Max Act: 5.2611. Min Act: -0.1700

Data Index: 271314 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 5.5423. Min Range: -5.5423

Max Act: 5.2611. Min Act: -0.1699

Data Index: 686488 (C4 (Web Text))

Max Activating Token Index: 365