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

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

Neuron 1777 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: 5.8370. Min Range: -5.8370

Max Act: 5.8057. Min Act: -0.1700

Data Index: 868180 (C4 (Web Text))

Max Activating Token Index: 294

Text #1

Max Range: 5.8370. Min Range: -5.8370

Max Act: 5.7432. Min Act: -0.1700

Data Index: 1168931 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 5.8370. Min Range: -5.8370

Max Act: 5.7432. Min Act: -0.1700

Data Index: 873585 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 5.8370. Min Range: -5.8370

Max Act: 5.8370. Min Act: -0.1700

Data Index: 365884 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 5.8370. Min Range: -5.8370

Max Act: 5.7745. Min Act: -0.1700

Data Index: 344298 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 5.8370. Min Range: -5.8370

Max Act: 5.7120. Min Act: -0.1700

Data Index: 417778 (C4 (Web Text))

Max Activating Token Index: 739

Text #6

Max Range: 5.8370. Min Range: -5.8370

Max Act: 5.7432. Min Act: -0.1700

Data Index: 723171 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 5.8370. Min Range: -5.8370

Max Act: 5.7120. Min Act: -0.1700

Data Index: 594485 (C4 (Web Text))

Max Activating Token Index: 729

Text #8

Max Range: 5.8370. Min Range: -5.8370

Max Act: 5.6807. Min Act: -0.1700

Data Index: 1013628 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 5.8370. Min Range: -5.8370

Max Act: 5.6807. Min Act: -0.1700

Data Index: 246467 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 5.8370. Min Range: -5.8370

Max Act: 5.6495. Min Act: -0.1700

Data Index: 1170894 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 5.8370. Min Range: -5.8370

Max Act: 5.7120. Min Act: -0.1700

Data Index: 1065944 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 5.8370. Min Range: -5.8370

Max Act: 5.6495. Min Act: -0.1700

Data Index: 357637 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 5.8370. Min Range: -5.8370

Max Act: 5.5557. Min Act: -0.1700

Data Index: 726099 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 5.8370. Min Range: -5.8370

Max Act: 5.5870. Min Act: -0.1700

Data Index: 756654 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 5.8370. Min Range: -5.8370

Max Act: 5.6182. Min Act: -0.1700

Data Index: 1118455 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 5.8370. Min Range: -5.8370

Max Act: 5.5870. Min Act: -0.1700

Data Index: 1270431 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 5.8370. Min Range: -5.8370

Max Act: 5.5870. Min Act: -0.1700

Data Index: 1046340 (C4 (Web Text))

Max Activating Token Index: 643

Text #18

Max Range: 5.8370. Min Range: -5.8370

Max Act: 5.6495. Min Act: -0.1700

Data Index: 433687 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 5.8370. Min Range: -5.8370

Max Act: 5.5870. Min Act: -0.1700

Data Index: 397723 (C4 (Web Text))

Max Activating Token Index: 633