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

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

Neuron 1065 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: 5.3649. Min Range: -5.3649

Max Act: 5.3649. Min Act: -0.1700

Data Index: 1240286 (C4 (Web Text))

Max Activating Token Index: 667

Text #1

Max Range: 5.3649. Min Range: -5.3649

Max Act: 5.2711. Min Act: -0.1700

Data Index: 302589 (C4 (Web Text))

Max Activating Token Index: 492

Text #2

Max Range: 5.3649. Min Range: -5.3649

Max Act: 5.2711. Min Act: -0.1700

Data Index: 1323418 (C4 (Web Text))

Max Activating Token Index: 385

Text #3

Max Range: 5.3649. Min Range: -5.3649

Max Act: 5.2711. Min Act: -0.1700

Data Index: 1306268 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 5.3649. Min Range: -5.3649

Max Act: 5.2399. Min Act: -0.1700

Data Index: 665064 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 5.3649. Min Range: -5.3649

Max Act: 5.1774. Min Act: -0.1700

Data Index: 174009 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 5.3649. Min Range: -5.3649

Max Act: 5.1774. Min Act: -0.1700

Data Index: 1292524 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 5.3649. Min Range: -5.3649

Max Act: 5.1774. Min Act: -0.1700

Data Index: 835508 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 5.3649. Min Range: -5.3649

Max Act: 5.0836. Min Act: -0.1700

Data Index: 1051283 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 5.3649. Min Range: -5.3649

Max Act: 5.0524. Min Act: -0.1700

Data Index: 320083 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 5.3649. Min Range: -5.3649

Max Act: 5.0211. Min Act: -0.1700

Data Index: 713961 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 5.3649. Min Range: -5.3649

Max Act: 5.0524. Min Act: -0.1700

Data Index: 164690 (C4 (Web Text))

Max Activating Token Index: 877

Text #12

Max Range: 5.3649. Min Range: -5.3649

Max Act: 4.9899. Min Act: -0.1700

Data Index: 308066 (C4 (Web Text))

Max Activating Token Index: 538

Text #13

Max Range: 5.3649. Min Range: -5.3649

Max Act: 5.0211. Min Act: -0.1700

Data Index: 1049003 (C4 (Web Text))

Max Activating Token Index: 150

Text #14

Max Range: 5.3649. Min Range: -5.3649

Max Act: 5.0211. Min Act: -0.1700

Data Index: 578137 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 5.3649. Min Range: -5.3649

Max Act: 5.0211. Min Act: -0.1700

Data Index: 112370 (C4 (Web Text))

Max Activating Token Index: 356

Text #16

Max Range: 5.3649. Min Range: -5.3649

Max Act: 4.9586. Min Act: -0.1700

Data Index: 936195 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 5.3649. Min Range: -5.3649

Max Act: 4.8961. Min Act: -0.1700

Data Index: 470449 (C4 (Web Text))

Max Activating Token Index: 933

Text #18

Max Range: 5.3649. Min Range: -5.3649

Max Act: 4.9586. Min Act: -0.1700

Data Index: 1233880 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 5.3649. Min Range: -5.3649

Max Act: 4.9274. Min Act: -0.1700

Data Index: 314094 (C4 (Web Text))

Max Activating Token Index: 220