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

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

Neuron 2046 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: 3.9898. Min Range: -3.9898

Max Act: 3.9898. Min Act: -0.1700

Data Index: 1189611 (C4 (Web Text))

Max Activating Token Index: 350

Text #1

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.9585. Min Act: -0.1700

Data Index: 1349391 (C4 (Web Text))

Max Activating Token Index: 461

Text #2

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.9429. Min Act: -0.1700

Data Index: 474621 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.9273. Min Act: -0.1700

Data Index: 498317 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.8804. Min Act: -0.1700

Data Index: 450921 (C4 (Web Text))

Max Activating Token Index: 230

Text #5

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.9585. Min Act: -0.1700

Data Index: 408222 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.9273. Min Act: -0.1700

Data Index: 400447 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.8804. Min Act: -0.1700

Data Index: 72483 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.8647. Min Act: -0.1700

Data Index: 1108562 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.8647. Min Act: -0.1700

Data Index: 998183 (C4 (Web Text))

Max Activating Token Index: 435

Text #10

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.8960. Min Act: -0.1700

Data Index: 1333647 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.8178. Min Act: -0.1700

Data Index: 1000238 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.9116. Min Act: -0.1700

Data Index: 140442 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.8334. Min Act: -0.1700

Data Index: 396595 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.7709. Min Act: -0.1700

Data Index: 324347 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.8334. Min Act: -0.1700

Data Index: 449969 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.8334. Min Act: -0.1700

Data Index: 1184869 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.8334. Min Act: -0.1700

Data Index: 436722 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.8334. Min Act: -0.1700

Data Index: 753623 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 3.9898. Min Range: -3.9898

Max Act: 3.7865. Min Act: -0.1700

Data Index: 1131154 (C4 (Web Text))

Max Activating Token Index: 331