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

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

Neuron 1763 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.7306. Min Range: -5.7306

Max Act: 5.7306. Min Act: -0.1700

Data Index: 326867 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 5.7306. Min Range: -5.7306

Max Act: 5.6681. Min Act: -0.1700

Data Index: 239005 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 5.7306. Min Range: -5.7306

Max Act: 5.5743. Min Act: -0.1700

Data Index: 947712 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 5.7306. Min Range: -5.7306

Max Act: 5.4493. Min Act: -0.1700

Data Index: 1260718 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 5.7306. Min Range: -5.7306

Max Act: 5.4493. Min Act: -0.1700

Data Index: 386255 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 5.7306. Min Range: -5.7306

Max Act: 5.4181. Min Act: -0.1700

Data Index: 56322 (C4 (Web Text))

Max Activating Token Index: 493

Text #6

Max Range: 5.7306. Min Range: -5.7306

Max Act: 5.4181. Min Act: -0.1700

Data Index: 345097 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 5.7306. Min Range: -5.7306

Max Act: 5.3868. Min Act: -0.1700

Data Index: 1006834 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 5.7306. Min Range: -5.7306

Max Act: 5.3868. Min Act: -0.1700

Data Index: 854317 (C4 (Web Text))

Max Activating Token Index: 754

Text #9

Max Range: 5.7306. Min Range: -5.7306

Max Act: 5.3556. Min Act: -0.1700

Data Index: 261971 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 5.7306. Min Range: -5.7306

Max Act: 5.3243. Min Act: -0.1700

Data Index: 648836 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 5.7306. Min Range: -5.7306

Max Act: 5.2618. Min Act: -0.1700

Data Index: 42040 (C4 (Web Text))

Max Activating Token Index: 629

Text #12

Max Range: 5.7306. Min Range: -5.7306

Max Act: 5.2306. Min Act: -0.1700

Data Index: 426183 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 5.7306. Min Range: -5.7306

Max Act: 5.2462. Min Act: -0.1700

Data Index: 263378 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 5.7306. Min Range: -5.7306

Max Act: 5.2618. Min Act: -0.1700

Data Index: 531703 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 5.7306. Min Range: -5.7306

Max Act: 5.1368. Min Act: -0.1700

Data Index: 946858 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 5.7306. Min Range: -5.7306

Max Act: 5.1993. Min Act: -0.1700

Data Index: 494852 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 5.7306. Min Range: -5.7306

Max Act: 5.1993. Min Act: -0.1700

Data Index: 975966 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 5.7306. Min Range: -5.7306

Max Act: 5.1525. Min Act: -0.1699

Data Index: 34091 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 5.7306. Min Range: -5.7306

Max Act: 5.1681. Min Act: -0.1700

Data Index: 1000752 (C4 (Web Text))

Max Activating Token Index: 591