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

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

Neuron 1829 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.8251. Min Range: -5.8251

Max Act: 5.8251. Min Act: -0.1700

Data Index: 632220 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 5.8251. Min Range: -5.8251

Max Act: 5.8251. Min Act: -0.1700

Data Index: 965880 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 5.8251. Min Range: -5.8251

Max Act: 5.7938. Min Act: -0.1700

Data Index: 653246 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 5.8251. Min Range: -5.8251

Max Act: 5.7626. Min Act: -0.1700

Data Index: 772112 (C4 (Web Text))

Max Activating Token Index: 750

Text #4

Max Range: 5.8251. Min Range: -5.8251

Max Act: 5.6376. Min Act: -0.1700

Data Index: 513182 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 5.8251. Min Range: -5.8251

Max Act: 5.5751. Min Act: -0.1700

Data Index: 887854 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 5.8251. Min Range: -5.8251

Max Act: 5.6063. Min Act: -0.1700

Data Index: 900522 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 5.8251. Min Range: -5.8251

Max Act: 5.6376. Min Act: -0.1700

Data Index: 839793 (C4 (Web Text))

Max Activating Token Index: 298

Text #8

Max Range: 5.8251. Min Range: -5.8251

Max Act: 5.5751. Min Act: -0.1700

Data Index: 797963 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 5.8251. Min Range: -5.8251

Max Act: 5.6063. Min Act: -0.1700

Data Index: 726227 (C4 (Web Text))

Max Activating Token Index: 858

Text #10

Max Range: 5.8251. Min Range: -5.8251

Max Act: 5.6376. Min Act: -0.1700

Data Index: 1192262 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 5.8251. Min Range: -5.8251

Max Act: 5.6063. Min Act: -0.1700

Data Index: 871916 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 5.8251. Min Range: -5.8251

Max Act: 5.6063. Min Act: -0.1700

Data Index: 554788 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 5.8251. Min Range: -5.8251

Max Act: 5.6063. Min Act: -0.1700

Data Index: 76051 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 5.8251. Min Range: -5.8251

Max Act: 5.5751. Min Act: -0.1700

Data Index: 648188 (C4 (Web Text))

Max Activating Token Index: 17

Text #15

Max Range: 5.8251. Min Range: -5.8251

Max Act: 5.5438. Min Act: -0.1700

Data Index: 639779 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 5.8251. Min Range: -5.8251

Max Act: 5.5438. Min Act: -0.1700

Data Index: 484656 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 5.8251. Min Range: -5.8251

Max Act: 5.5438. Min Act: -0.1700

Data Index: 856593 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 5.8251. Min Range: -5.8251

Max Act: 5.4813. Min Act: -0.1700

Data Index: 94703 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 5.8251. Min Range: -5.8251

Max Act: 5.5438. Min Act: -0.1700

Data Index: 98908 (C4 (Web Text))

Max Activating Token Index: 653