Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1032 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.6269. Min Range: -3.6269

Max Act: 3.6269. Min Act: -0.1700

Data Index: 974917 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 3.6269. Min Range: -3.6269

Max Act: 3.6053. Min Act: -0.1700

Data Index: 434996 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 3.6269. Min Range: -3.6269

Max Act: 3.6008. Min Act: -0.1696

Data Index: 112775 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 3.6269. Min Range: -3.6269

Max Act: 3.5553. Min Act: -0.1700

Data Index: 1045929 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 3.6269. Min Range: -3.6269

Max Act: 3.5727. Min Act: -0.1700

Data Index: 1232608 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 3.6269. Min Range: -3.6269

Max Act: 3.5260. Min Act: -0.1700

Data Index: 451518 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 3.6269. Min Range: -3.6269

Max Act: 3.5306. Min Act: -0.1700

Data Index: 27642 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 3.6269. Min Range: -3.6269

Max Act: 3.5192. Min Act: -0.1700

Data Index: 667825 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 3.6269. Min Range: -3.6269

Max Act: 3.5306. Min Act: -0.1699

Data Index: 27538 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 3.6269. Min Range: -3.6269

Max Act: 3.5195. Min Act: -0.1698

Data Index: 897015 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 3.6269. Min Range: -3.6269

Max Act: 3.4954. Min Act: -0.1700

Data Index: 615206 (C4 (Web Text))

Max Activating Token Index: 837

Text #11

Max Range: 3.6269. Min Range: -3.6269

Max Act: 3.4812. Min Act: -0.1700

Data Index: 1048573 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 3.6269. Min Range: -3.6269

Max Act: 3.4923. Min Act: -0.1700

Data Index: 931226 (C4 (Web Text))

Max Activating Token Index: 514

Text #13

Max Range: 3.6269. Min Range: -3.6269

Max Act: 3.4523. Min Act: -0.1700

Data Index: 1050270 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 3.6269. Min Range: -3.6269

Max Act: 3.4510. Min Act: -0.1700

Data Index: 1300770 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 3.6269. Min Range: -3.6269

Max Act: 3.4658. Min Act: -0.1700

Data Index: 602502 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 3.6269. Min Range: -3.6269

Max Act: 3.4621. Min Act: -0.1700

Data Index: 1117814 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 3.6269. Min Range: -3.6269

Max Act: 3.4607. Min Act: -0.1700

Data Index: 668797 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 3.6269. Min Range: -3.6269

Max Act: 3.4221. Min Act: -0.1700

Data Index: 887637 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 3.6269. Min Range: -3.6269

Max Act: 3.4082. Min Act: -0.1700

Data Index: 967065 (C4 (Web Text))

Max Activating Token Index: 796