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

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

Neuron 1987 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.6214. Min Act: -0.1700

Data Index: 1311573 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.6057. Min Act: -0.1700

Data Index: 1044322 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.5901. Min Act: -0.1700

Data Index: 1042857 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.5901. Min Act: -0.1700

Data Index: 94984 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.5587. Min Act: -0.1700

Data Index: 972122 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.5274. Min Act: -0.1700

Data Index: 179808 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.5274. Min Act: -0.1700

Data Index: 358742 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.4961. Min Act: -0.1700

Data Index: 667851 (C4 (Web Text))

Max Activating Token Index: 179

Text #8

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.4647. Min Act: -0.1700

Data Index: 1207454 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.4647. Min Act: -0.1700

Data Index: 918807 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.4491. Min Act: -0.1700

Data Index: 508542 (C4 (Web Text))

Max Activating Token Index: 605

Text #11

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.4491. Min Act: -0.1700

Data Index: 894740 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.4334. Min Act: -0.1700

Data Index: 1210177 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.4020. Min Act: -0.1700

Data Index: 52717 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.4177. Min Act: -0.1700

Data Index: 1336324 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.4177. Min Act: -0.1700

Data Index: 1113219 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.4177. Min Act: -0.1700

Data Index: 574591 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.4020. Min Act: -0.1700

Data Index: 1270949 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.4177. Min Act: -0.1700

Data Index: 66563 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 3.6214. Min Range: -3.6214

Max Act: 3.4020. Min Act: -0.1700

Data Index: 936966 (C4 (Web Text))

Max Activating Token Index: 688