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

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

Neuron 2035 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: 3.5564. Min Range: -3.5564

Max Act: 3.5564. Min Act: -0.1700

Data Index: 796491 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.4937. Min Act: -0.1700

Data Index: 1029180 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.4780. Min Act: -0.1700

Data Index: 435481 (C4 (Web Text))

Max Activating Token Index: 234

Text #3

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.4624. Min Act: -0.1700

Data Index: 826174 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.4624. Min Act: -0.1700

Data Index: 411359 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.4937. Min Act: -0.1700

Data Index: 454006 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.4780. Min Act: -0.1700

Data Index: 829619 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.4467. Min Act: -0.1700

Data Index: 926314 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.4310. Min Act: -0.1700

Data Index: 837813 (C4 (Web Text))

Max Activating Token Index: 717

Text #9

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.4624. Min Act: -0.1700

Data Index: 282145 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.4310. Min Act: -0.1700

Data Index: 915283 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.3839. Min Act: -0.1700

Data Index: 809385 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.4310. Min Act: -0.1700

Data Index: 328682 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.4153. Min Act: -0.1700

Data Index: 264676 (C4 (Web Text))

Max Activating Token Index: 655

Text #14

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.3839. Min Act: -0.1700

Data Index: 968371 (C4 (Web Text))

Max Activating Token Index: 807

Text #15

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.4153. Min Act: -0.1700

Data Index: 804466 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.3839. Min Act: -0.1700

Data Index: 446397 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.3683. Min Act: -0.1700

Data Index: 404280 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.3839. Min Act: -0.1700

Data Index: 1013893 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 3.5564. Min Range: -3.5564

Max Act: 3.3839. Min Act: -0.1700

Data Index: 3010 (C4 (Web Text))

Max Activating Token Index: 661