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

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

Neuron 1507 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: 3.8120. Min Range: -3.8120

Max Act: 3.8120. Min Act: -0.1700

Data Index: 1024007 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.8120. Min Act: -0.1700

Data Index: 516128 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.7182. Min Act: -0.1700

Data Index: 635264 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6869. Min Act: -0.1700

Data Index: 228378 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6869. Min Act: -0.1700

Data Index: 640891 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.7182. Min Act: -0.1700

Data Index: 973739 (C4 (Web Text))

Max Activating Token Index: 339

Text #6

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.7182. Min Act: -0.1700

Data Index: 414846 (C4 (Web Text))

Max Activating Token Index: 264

Text #7

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6869. Min Act: -0.1700

Data Index: 1036986 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.7182. Min Act: -0.1700

Data Index: 1042952 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.7182. Min Act: -0.1700

Data Index: 1075718 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6869. Min Act: -0.1700

Data Index: 1243392 (C4 (Web Text))

Max Activating Token Index: 269

Text #11

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6869. Min Act: -0.1700

Data Index: 1230748 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6869. Min Act: -0.1700

Data Index: 920930 (C4 (Web Text))

Max Activating Token Index: 304

Text #13

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6556. Min Act: -0.1700

Data Index: 320926 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6556. Min Act: -0.1700

Data Index: 147417 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6869. Min Act: -0.1700

Data Index: 989897 (C4 (Web Text))

Max Activating Token Index: 794

Text #16

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6556. Min Act: -0.1700

Data Index: 680000 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6869. Min Act: -0.1700

Data Index: 1145050 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6869. Min Act: -0.1700

Data Index: 538041 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 3.8120. Min Range: -3.8120

Max Act: 3.6869. Min Act: -0.1700

Data Index: 1198728 (C4 (Web Text))

Max Activating Token Index: 770