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

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

Neuron 1134 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: 3.6913. Min Range: -3.6913

Max Act: 3.6913. Min Act: -0.1700

Data Index: 486084 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.3466. Min Act: -0.1700

Data Index: 385859 (C4 (Web Text))

Max Activating Token Index: 605

Text #2

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.3466. Min Act: -0.1700

Data Index: 1245485 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.3466. Min Act: -0.1700

Data Index: 971040 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.3152. Min Act: -0.1700

Data Index: 108178 (C4 (Web Text))

Max Activating Token Index: 674

Text #5

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.2524. Min Act: -0.1700

Data Index: 722977 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.3466. Min Act: -0.1700

Data Index: 363524 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.2524. Min Act: -0.1700

Data Index: 153500 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.2838. Min Act: -0.1700

Data Index: 1197433 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.2524. Min Act: -0.1700

Data Index: 287357 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.2209. Min Act: -0.1700

Data Index: 115831 (C4 (Web Text))

Max Activating Token Index: 284

Text #11

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.2209. Min Act: -0.1700

Data Index: 1074722 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.2209. Min Act: -0.1700

Data Index: 72299 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.2524. Min Act: -0.1700

Data Index: 540917 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.1895. Min Act: -0.1700

Data Index: 614672 (C4 (Web Text))

Max Activating Token Index: 25

Text #15

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.2209. Min Act: -0.1700

Data Index: 1357131 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.1895. Min Act: -0.1700

Data Index: 128474 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.1580. Min Act: -0.1700

Data Index: 234969 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.2209. Min Act: -0.1700

Data Index: 879837 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 3.6913. Min Range: -3.6913

Max Act: 3.2209. Min Act: -0.1700

Data Index: 981468 (C4 (Web Text))

Max Activating Token Index: 723