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

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

Neuron 862 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.3376. Min Act: -0.1700

Data Index: 1287311 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.2905. Min Act: -0.1700

Data Index: 1196736 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.2119. Min Act: -0.1700

Data Index: 828078 (C4 (Web Text))

Max Activating Token Index: 744

Text #3

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.2748. Min Act: -0.1700

Data Index: 389160 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.2434. Min Act: -0.1700

Data Index: 40687 (C4 (Web Text))

Max Activating Token Index: 714

Text #5

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.2277. Min Act: -0.1700

Data Index: 913273 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.2119. Min Act: -0.1700

Data Index: 1015607 (C4 (Web Text))

Max Activating Token Index: 932

Text #7

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.1805. Min Act: -0.1700

Data Index: 896660 (C4 (Web Text))

Max Activating Token Index: 893

Text #8

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.1805. Min Act: -0.1700

Data Index: 387902 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.2277. Min Act: -0.1700

Data Index: 304607 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.1805. Min Act: -0.1700

Data Index: 1165529 (C4 (Web Text))

Max Activating Token Index: 843

Text #11

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.1490. Min Act: -0.1700

Data Index: 1173767 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.1490. Min Act: -0.1700

Data Index: 926802 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.1647. Min Act: -0.1700

Data Index: 457880 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.1647. Min Act: -0.1700

Data Index: 336130 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.1805. Min Act: -0.1700

Data Index: 637099 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.1490. Min Act: -0.1700

Data Index: 1079100 (C4 (Web Text))

Max Activating Token Index: 647

Text #17

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.1490. Min Act: -0.1700

Data Index: 1203635 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.1490. Min Act: -0.1700

Data Index: 546278 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 3.3376. Min Range: -3.3376

Max Act: 3.1017. Min Act: -0.1700

Data Index: 1341270 (C4 (Web Text))

Max Activating Token Index: 809