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

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

Neuron 417 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: 3.8779. Min Range: -3.8779

Max Act: 3.8779. Min Act: -0.1700

Data Index: 117326 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 3.8779. Min Range: -3.8779

Max Act: 3.8153. Min Act: -0.1700

Data Index: 1045509 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 3.8779. Min Range: -3.8779

Max Act: 3.6589. Min Act: -0.1700

Data Index: 307212 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 3.8779. Min Range: -3.8779

Max Act: 3.6902. Min Act: -0.1700

Data Index: 713825 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 3.8779. Min Range: -3.8779

Max Act: 3.6902. Min Act: -0.1700

Data Index: 423345 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 3.8779. Min Range: -3.8779

Max Act: 3.6589. Min Act: -0.1700

Data Index: 621243 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 3.8779. Min Range: -3.8779

Max Act: 3.6589. Min Act: -0.1700

Data Index: 512503 (C4 (Web Text))

Max Activating Token Index: 265

Text #7

Max Range: 3.8779. Min Range: -3.8779

Max Act: 3.6275. Min Act: -0.1700

Data Index: 1319312 (C4 (Web Text))

Max Activating Token Index: 59

Text #8

Max Range: 3.8779. Min Range: -3.8779

Max Act: 3.5962. Min Act: -0.1700

Data Index: 388368 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 3.8779. Min Range: -3.8779

Max Act: 3.5962. Min Act: -0.1700

Data Index: 875929 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 3.8779. Min Range: -3.8779

Max Act: 3.5962. Min Act: -0.1700

Data Index: 442564 (C4 (Web Text))

Max Activating Token Index: 889

Text #11

Max Range: 3.8779. Min Range: -3.8779

Max Act: 3.5962. Min Act: -0.1700

Data Index: 473793 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 3.8779. Min Range: -3.8779

Max Act: 3.5962. Min Act: -0.1700

Data Index: 1079657 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 3.8779. Min Range: -3.8779

Max Act: 3.5962. Min Act: -0.1700

Data Index: 228777 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 3.8779. Min Range: -3.8779

Max Act: 3.6275. Min Act: -0.1700

Data Index: 1189835 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 3.8779. Min Range: -3.8779

Max Act: 3.5962. Min Act: -0.1700

Data Index: 35696 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 3.8779. Min Range: -3.8779

Max Act: 3.5962. Min Act: -0.1700

Data Index: 684903 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 3.8779. Min Range: -3.8779

Max Act: 3.5649. Min Act: -0.1700

Data Index: 478699 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 3.8779. Min Range: -3.8779

Max Act: 3.5336. Min Act: -0.1700

Data Index: 371476 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 3.8779. Min Range: -3.8779

Max Act: 3.5649. Min Act: -0.1700

Data Index: 532816 (C4 (Web Text))

Max Activating Token Index: 901