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

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

Neuron 21 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: 6.1911. Min Range: -6.1911

Max Act: 6.1911. Min Act: -0.1700

Data Index: 53015 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 6.1911. Min Range: -6.1911

Max Act: 5.7849. Min Act: -0.1700

Data Index: 234320 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 6.1911. Min Range: -6.1911

Max Act: 5.7224. Min Act: -0.1700

Data Index: 501936 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 6.1911. Min Range: -6.1911

Max Act: 5.7224. Min Act: -0.1700

Data Index: 605863 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 6.1911. Min Range: -6.1911

Max Act: 5.7224. Min Act: -0.1700

Data Index: 294947 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 6.1911. Min Range: -6.1911

Max Act: 5.6911. Min Act: -0.1700

Data Index: 1334484 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 6.1911. Min Range: -6.1911

Max Act: 5.6911. Min Act: -0.1700

Data Index: 1094055 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 6.1911. Min Range: -6.1911

Max Act: 5.6599. Min Act: -0.1700

Data Index: 32189 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 6.1911. Min Range: -6.1911

Max Act: 5.7224. Min Act: -0.1700

Data Index: 231007 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 6.1911. Min Range: -6.1911

Max Act: 5.5974. Min Act: -0.1700

Data Index: 383625 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 6.1911. Min Range: -6.1911

Max Act: 5.5349. Min Act: -0.1700

Data Index: 1317374 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 6.1911. Min Range: -6.1911

Max Act: 5.5036. Min Act: -0.1700

Data Index: 281595 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 6.1911. Min Range: -6.1911

Max Act: 5.5349. Min Act: -0.1700

Data Index: 643922 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 6.1911. Min Range: -6.1911

Max Act: 5.4724. Min Act: -0.1700

Data Index: 543575 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 6.1911. Min Range: -6.1911

Max Act: 5.5349. Min Act: -0.1700

Data Index: 426991 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 6.1911. Min Range: -6.1911

Max Act: 5.4724. Min Act: -0.1700

Data Index: 817219 (C4 (Web Text))

Max Activating Token Index: 988

Text #16

Max Range: 6.1911. Min Range: -6.1911

Max Act: 5.5349. Min Act: -0.1700

Data Index: 1337081 (C4 (Web Text))

Max Activating Token Index: 479

Text #17

Max Range: 6.1911. Min Range: -6.1911

Max Act: 5.5036. Min Act: -0.1700

Data Index: 16253 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 6.1911. Min Range: -6.1911

Max Act: 5.4724. Min Act: -0.1700

Data Index: 12282 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 6.1911. Min Range: -6.1911

Max Act: 5.4724. Min Act: -0.1700

Data Index: 141131 (C4 (Web Text))

Max Activating Token Index: 704