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

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

Neuron 1580 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2619. Min Range: -3.2619

Max Act: 3.2619. Min Act: -0.1700

Data Index: 847548 (C4 (Web Text))

Max Activating Token Index: 267

Text #1

Max Range: 3.2619. Min Range: -3.2619

Max Act: 3.2305. Min Act: -0.1700

Data Index: 220112 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 3.2619. Min Range: -3.2619

Max Act: 3.1833. Min Act: -0.1700

Data Index: 449876 (C4 (Web Text))

Max Activating Token Index: 199

Text #3

Max Range: 3.2619. Min Range: -3.2619

Max Act: 3.1675. Min Act: -0.1700

Data Index: 218612 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 3.2619. Min Range: -3.2619

Max Act: 3.1518. Min Act: -0.1700

Data Index: 446288 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 3.2619. Min Range: -3.2619

Max Act: 3.1045. Min Act: -0.1700

Data Index: 813275 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 3.2619. Min Range: -3.2619

Max Act: 3.0730. Min Act: -0.1700

Data Index: 311202 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 3.2619. Min Range: -3.2619

Max Act: 3.0730. Min Act: -0.1700

Data Index: 25405 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 3.2619. Min Range: -3.2619

Max Act: 3.0730. Min Act: -0.1700

Data Index: 699998 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 3.2619. Min Range: -3.2619

Max Act: 3.0888. Min Act: -0.1700

Data Index: 763709 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 3.2619. Min Range: -3.2619

Max Act: 3.0730. Min Act: -0.1700

Data Index: 698698 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 3.2619. Min Range: -3.2619

Max Act: 3.0414. Min Act: -0.1700

Data Index: 381715 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 3.2619. Min Range: -3.2619

Max Act: 3.0572. Min Act: -0.1700

Data Index: 329875 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 3.2619. Min Range: -3.2619

Max Act: 3.0256. Min Act: -0.1700

Data Index: 984144 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 3.2619. Min Range: -3.2619

Max Act: 3.0414. Min Act: -0.1700

Data Index: 123173 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 3.2619. Min Range: -3.2619

Max Act: 3.0414. Min Act: -0.1700

Data Index: 196535 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 3.2619. Min Range: -3.2619

Max Act: 3.0256. Min Act: -0.1700

Data Index: 409827 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 3.2619. Min Range: -3.2619

Max Act: 3.0256. Min Act: -0.1700

Data Index: 635983 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 3.2619. Min Range: -3.2619

Max Act: 3.0256. Min Act: -0.1700

Data Index: 976397 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 3.2619. Min Range: -3.2619

Max Act: 3.0256. Min Act: -0.1700

Data Index: 573306 (C4 (Web Text))

Max Activating Token Index: 499