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

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

Neuron 402 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: 6.2180. Min Range: -6.2180

Max Act: 6.2180. Min Act: -0.1700

Data Index: 1011493 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 6.2180. Min Range: -6.2180

Max Act: 5.9055. Min Act: -0.1700

Data Index: 261629 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 6.2180. Min Range: -6.2180

Max Act: 5.8430. Min Act: -0.1700

Data Index: 55188 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 6.2180. Min Range: -6.2180

Max Act: 5.7493. Min Act: -0.1700

Data Index: 1190599 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 6.2180. Min Range: -6.2180

Max Act: 5.8118. Min Act: -0.1700

Data Index: 918436 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 6.2180. Min Range: -6.2180

Max Act: 5.7180. Min Act: -0.1700

Data Index: 460804 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 6.2180. Min Range: -6.2180

Max Act: 5.7180. Min Act: -0.1700

Data Index: 468725 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 6.2180. Min Range: -6.2180

Max Act: 5.6868. Min Act: -0.1699

Data Index: 675483 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 6.2180. Min Range: -6.2180

Max Act: 5.6868. Min Act: -0.1700

Data Index: 1324052 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 6.2180. Min Range: -6.2180

Max Act: 5.6868. Min Act: -0.1700

Data Index: 114328 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 6.2180. Min Range: -6.2180

Max Act: 5.6555. Min Act: -0.1700

Data Index: 453833 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 6.2180. Min Range: -6.2180

Max Act: 5.6555. Min Act: -0.1700

Data Index: 139437 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 6.2180. Min Range: -6.2180

Max Act: 5.6868. Min Act: -0.1700

Data Index: 689610 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 6.2180. Min Range: -6.2180

Max Act: 5.6555. Min Act: -0.1699

Data Index: 692009 (C4 (Web Text))

Max Activating Token Index: 470

Text #14

Max Range: 6.2180. Min Range: -6.2180

Max Act: 5.6243. Min Act: -0.1700

Data Index: 1196619 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 6.2180. Min Range: -6.2180

Max Act: 5.6243. Min Act: -0.1700

Data Index: 573395 (C4 (Web Text))

Max Activating Token Index: 338

Text #16

Max Range: 6.2180. Min Range: -6.2180

Max Act: 5.6243. Min Act: -0.1700

Data Index: 20223 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 6.2180. Min Range: -6.2180

Max Act: 5.6555. Min Act: -0.1700

Data Index: 247580 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 6.2180. Min Range: -6.2180

Max Act: 5.6555. Min Act: -0.1700

Data Index: 692646 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 6.2180. Min Range: -6.2180

Max Act: 5.6243. Min Act: -0.1700

Data Index: 907609 (C4 (Web Text))

Max Activating Token Index: 947