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

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

Neuron 1339 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.5740. Min Act: -0.1700

Data Index: 1330561 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.5427. Min Act: -0.1700

Data Index: 361332 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.4801. Min Act: -0.1700

Data Index: 812175 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.4487. Min Act: -0.1700

Data Index: 1043387 (C4 (Web Text))

Max Activating Token Index: 554

Text #4

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.4487. Min Act: -0.1700

Data Index: 992664 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.4801. Min Act: -0.1700

Data Index: 1190338 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.4801. Min Act: -0.1700

Data Index: 1126067 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.4173. Min Act: -0.1700

Data Index: 39166 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.3232. Min Act: -0.1700

Data Index: 188115 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.4487. Min Act: -0.1700

Data Index: 658483 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.3546. Min Act: -0.1700

Data Index: 391638 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.4173. Min Act: -0.1700

Data Index: 547084 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.3546. Min Act: -0.1700

Data Index: 1403733 (Python Code)

Max Activating Token Index: 533

Text #13

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.3860. Min Act: -0.1700

Data Index: 626288 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.3232. Min Act: -0.1700

Data Index: 523437 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.3546. Min Act: -0.1700

Data Index: 87038 (C4 (Web Text))

Max Activating Token Index: 981

Text #16

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.3860. Min Act: -0.1700

Data Index: 315226 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.2918. Min Act: -0.1700

Data Index: 1082197 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.3546. Min Act: -0.1700

Data Index: 536746 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 3.5740. Min Range: -3.5740

Max Act: 3.3232. Min Act: -0.1700

Data Index: 1014853 (C4 (Web Text))

Max Activating Token Index: 619