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

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

Neuron 1613 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.7491. Min Range: -7.7491

Max Act: 7.7491. Min Act: -0.1700

Data Index: 472150 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 7.7491. Min Range: -7.7491

Max Act: 7.7491. Min Act: -0.1700

Data Index: 544526 (C4 (Web Text))

Max Activating Token Index: 499

Text #2

Max Range: 7.7491. Min Range: -7.7491

Max Act: 7.5616. Min Act: -0.1700

Data Index: 738702 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 7.7491. Min Range: -7.7491

Max Act: 7.5616. Min Act: -0.1700

Data Index: 1002714 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 7.7491. Min Range: -7.7491

Max Act: 7.4991. Min Act: -0.1695

Data Index: 491901 (C4 (Web Text))

Max Activating Token Index: 388

Text #5

Max Range: 7.7491. Min Range: -7.7491

Max Act: 7.4991. Min Act: -0.1700

Data Index: 637163 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 7.7491. Min Range: -7.7491

Max Act: 7.4991. Min Act: -0.1700

Data Index: 106339 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 7.7491. Min Range: -7.7491

Max Act: 7.4366. Min Act: -0.1700

Data Index: 1089823 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 7.7491. Min Range: -7.7491

Max Act: 7.3741. Min Act: -0.1695

Data Index: 1279602 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 7.7491. Min Range: -7.7491

Max Act: 7.4366. Min Act: -0.1700

Data Index: 1185134 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 7.7491. Min Range: -7.7491

Max Act: 7.4366. Min Act: -0.1699

Data Index: 270218 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 7.7491. Min Range: -7.7491

Max Act: 7.4366. Min Act: -0.1700

Data Index: 295235 (C4 (Web Text))

Max Activating Token Index: 508

Text #12

Max Range: 7.7491. Min Range: -7.7491

Max Act: 7.3116. Min Act: -0.1700

Data Index: 810982 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 7.7491. Min Range: -7.7491

Max Act: 7.3116. Min Act: -0.1700

Data Index: 209156 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 7.7491. Min Range: -7.7491

Max Act: 7.3741. Min Act: -0.1700

Data Index: 475002 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 7.7491. Min Range: -7.7491

Max Act: 7.3116. Min Act: -0.1700

Data Index: 1089877 (C4 (Web Text))

Max Activating Token Index: 758

Text #16

Max Range: 7.7491. Min Range: -7.7491

Max Act: 7.3741. Min Act: -0.1699

Data Index: 376366 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 7.7491. Min Range: -7.7491

Max Act: 7.3741. Min Act: -0.1700

Data Index: 907780 (C4 (Web Text))

Max Activating Token Index: 109

Text #18

Max Range: 7.7491. Min Range: -7.7491

Max Act: 7.3116. Min Act: -0.1700

Data Index: 1127 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 7.7491. Min Range: -7.7491

Max Act: 7.3116. Min Act: -0.1700

Data Index: 406901 (C4 (Web Text))

Max Activating Token Index: 504