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

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

Neuron 807 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5449. Min Range: -3.5449

Max Act: 3.5449. Min Act: -0.1700

Data Index: 1049830 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 3.5449. Min Range: -3.5449

Max Act: 3.5292. Min Act: -0.1700

Data Index: 473424 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 3.5449. Min Range: -3.5449

Max Act: 3.4822. Min Act: -0.1700

Data Index: 398202 (C4 (Web Text))

Max Activating Token Index: 521

Text #3

Max Range: 3.5449. Min Range: -3.5449

Max Act: 3.4822. Min Act: -0.1700

Data Index: 167863 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 3.5449. Min Range: -3.5449

Max Act: 3.4822. Min Act: -0.1700

Data Index: 782705 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 3.5449. Min Range: -3.5449

Max Act: 3.4509. Min Act: -0.1700

Data Index: 1142420 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 3.5449. Min Range: -3.5449

Max Act: 3.4822. Min Act: -0.1700

Data Index: 429880 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 3.5449. Min Range: -3.5449

Max Act: 3.4509. Min Act: -0.1700

Data Index: 579556 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 3.5449. Min Range: -3.5449

Max Act: 3.3882. Min Act: -0.1700

Data Index: 128398 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 3.5449. Min Range: -3.5449

Max Act: 3.3882. Min Act: -0.1700

Data Index: 564807 (C4 (Web Text))

Max Activating Token Index: 280

Text #10

Max Range: 3.5449. Min Range: -3.5449

Max Act: 3.3568. Min Act: -0.1700

Data Index: 1059545 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 3.5449. Min Range: -3.5449

Max Act: 3.3882. Min Act: -0.1700

Data Index: 118156 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 3.5449. Min Range: -3.5449

Max Act: 3.4039. Min Act: -0.1700

Data Index: 1074406 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 3.5449. Min Range: -3.5449

Max Act: 3.3882. Min Act: -0.1700

Data Index: 582766 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 3.5449. Min Range: -3.5449

Max Act: 3.3725. Min Act: -0.1700

Data Index: 293143 (C4 (Web Text))

Max Activating Token Index: 826

Text #15

Max Range: 3.5449. Min Range: -3.5449

Max Act: 3.3568. Min Act: -0.1700

Data Index: 1334764 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 3.5449. Min Range: -3.5449

Max Act: 3.3568. Min Act: -0.1700

Data Index: 1205483 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 3.5449. Min Range: -3.5449

Max Act: 3.3725. Min Act: -0.1700

Data Index: 582771 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 3.5449. Min Range: -3.5449

Max Act: 3.3097. Min Act: -0.1700

Data Index: 1438545 (Python Code)

Max Activating Token Index: 760

Text #19

Max Range: 3.5449. Min Range: -3.5449

Max Act: 3.3568. Min Act: -0.1700

Data Index: 398314 (C4 (Web Text))

Max Activating Token Index: 153