Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 40 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 8.7779. Min Range: -8.7779

Max Act: 8.7779. Min Act: -0.1700

Data Index: 573069 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 8.7779. Min Range: -8.7779

Max Act: 8.7154. Min Act: -0.1700

Data Index: 307604 (C4 (Web Text))

Max Activating Token Index: 136

Text #2

Max Range: 8.7779. Min Range: -8.7779

Max Act: 8.7779. Min Act: -0.1700

Data Index: 632507 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 8.7779. Min Range: -8.7779

Max Act: 8.5904. Min Act: -0.1700

Data Index: 1322868 (C4 (Web Text))

Max Activating Token Index: 845

Text #4

Max Range: 8.7779. Min Range: -8.7779

Max Act: 8.4654. Min Act: -0.1700

Data Index: 808454 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 8.7779. Min Range: -8.7779

Max Act: 8.4654. Min Act: -0.1699

Data Index: 902871 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 8.7779. Min Range: -8.7779

Max Act: 8.4654. Min Act: -0.1699

Data Index: 813483 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 8.7779. Min Range: -8.7779

Max Act: 8.3404. Min Act: -0.1700

Data Index: 957850 (C4 (Web Text))

Max Activating Token Index: 599

Text #8

Max Range: 8.7779. Min Range: -8.7779

Max Act: 8.4654. Min Act: -0.1700

Data Index: 85358 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 8.7779. Min Range: -8.7779

Max Act: 8.4029. Min Act: -0.1700

Data Index: 545558 (C4 (Web Text))

Max Activating Token Index: 520

Text #10

Max Range: 8.7779. Min Range: -8.7779

Max Act: 8.2779. Min Act: -0.1700

Data Index: 1328434 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 8.7779. Min Range: -8.7779

Max Act: 8.1529. Min Act: -0.1700

Data Index: 989903 (C4 (Web Text))

Max Activating Token Index: 390

Text #12

Max Range: 8.7779. Min Range: -8.7779

Max Act: 8.2779. Min Act: -0.1700

Data Index: 1358437 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 8.7779. Min Range: -8.7779

Max Act: 8.2154. Min Act: -0.1700

Data Index: 296424 (C4 (Web Text))

Max Activating Token Index: 516

Text #14

Max Range: 8.7779. Min Range: -8.7779

Max Act: 8.2779. Min Act: -0.1700

Data Index: 51316 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 8.7779. Min Range: -8.7779

Max Act: 8.2154. Min Act: -0.1700

Data Index: 463785 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 8.7779. Min Range: -8.7779

Max Act: 8.2154. Min Act: -0.1700

Data Index: 915408 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 8.7779. Min Range: -8.7779

Max Act: 8.1529. Min Act: -0.1700

Data Index: 681360 (C4 (Web Text))

Max Activating Token Index: 213

Text #18

Max Range: 8.7779. Min Range: -8.7779

Max Act: 8.1529. Min Act: -0.1699

Data Index: 951465 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 8.7779. Min Range: -8.7779

Max Act: 8.1529. Min Act: -0.1700

Data Index: 1052655 (C4 (Web Text))

Max Activating Token Index: 335