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

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

Neuron 780 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1357. Min Range: -5.1357

Max Act: 5.1357. Min Act: -0.1700

Data Index: 239125 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 5.1357. Min Range: -5.1357

Max Act: 5.1357. Min Act: -0.1700

Data Index: 473639 (C4 (Web Text))

Max Activating Token Index: 277

Text #2

Max Range: 5.1357. Min Range: -5.1357

Max Act: 5.1357. Min Act: -0.1700

Data Index: 1088126 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 5.1357. Min Range: -5.1357

Max Act: 5.1357. Min Act: -0.1700

Data Index: 1003998 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 5.1357. Min Range: -5.1357

Max Act: 5.1357. Min Act: -0.1700

Data Index: 29806 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 5.1357. Min Range: -5.1357

Max Act: 5.1357. Min Act: -0.1700

Data Index: 792402 (C4 (Web Text))

Max Activating Token Index: 855

Text #6

Max Range: 5.1357. Min Range: -5.1357

Max Act: 5.1357. Min Act: -0.1700

Data Index: 730167 (C4 (Web Text))

Max Activating Token Index: 831

Text #7

Max Range: 5.1357. Min Range: -5.1357

Max Act: 5.1045. Min Act: -0.1700

Data Index: 154711 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 5.1357. Min Range: -5.1357

Max Act: 5.0732. Min Act: -0.1700

Data Index: 331617 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 5.1357. Min Range: -5.1357

Max Act: 5.0732. Min Act: -0.1700

Data Index: 781732 (C4 (Web Text))

Max Activating Token Index: 979

Text #10

Max Range: 5.1357. Min Range: -5.1357

Max Act: 5.0732. Min Act: -0.1700

Data Index: 1142992 (C4 (Web Text))

Max Activating Token Index: 302

Text #11

Max Range: 5.1357. Min Range: -5.1357

Max Act: 5.0732. Min Act: -0.1700

Data Index: 67993 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 5.1357. Min Range: -5.1357

Max Act: 5.0419. Min Act: -0.1700

Data Index: 873235 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 5.1357. Min Range: -5.1357

Max Act: 5.0419. Min Act: -0.1700

Data Index: 144674 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 5.1357. Min Range: -5.1357

Max Act: 4.9794. Min Act: -0.1699

Data Index: 174649 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 5.1357. Min Range: -5.1357

Max Act: 5.0419. Min Act: -0.1700

Data Index: 936918 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 5.1357. Min Range: -5.1357

Max Act: 5.0732. Min Act: -0.1700

Data Index: 427373 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 5.1357. Min Range: -5.1357

Max Act: 5.0107. Min Act: -0.1700

Data Index: 317642 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 5.1357. Min Range: -5.1357

Max Act: 5.0419. Min Act: -0.1700

Data Index: 666619 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 5.1357. Min Range: -5.1357

Max Act: 5.0107. Min Act: -0.1700

Data Index: 639081 (C4 (Web Text))

Max Activating Token Index: 924