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

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

Neuron 1073 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: 3.8713. Min Range: -3.8713

Max Act: 3.8713. Min Act: -0.1700

Data Index: 178635 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 3.8713. Min Range: -3.8713

Max Act: 3.7149. Min Act: -0.1700

Data Index: 800629 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 3.8713. Min Range: -3.8713

Max Act: 3.6836. Min Act: -0.1700

Data Index: 176273 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 3.8713. Min Range: -3.8713

Max Act: 3.6210. Min Act: -0.1700

Data Index: 361026 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 3.8713. Min Range: -3.8713

Max Act: 3.6523. Min Act: -0.1700

Data Index: 955256 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 3.8713. Min Range: -3.8713

Max Act: 3.6210. Min Act: -0.1700

Data Index: 1333137 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 3.8713. Min Range: -3.8713

Max Act: 3.5583. Min Act: -0.1700

Data Index: 561495 (C4 (Web Text))

Max Activating Token Index: 901

Text #7

Max Range: 3.8713. Min Range: -3.8713

Max Act: 3.5896. Min Act: -0.1700

Data Index: 923607 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 3.8713. Min Range: -3.8713

Max Act: 3.5896. Min Act: -0.1700

Data Index: 1321101 (C4 (Web Text))

Max Activating Token Index: 483

Text #9

Max Range: 3.8713. Min Range: -3.8713

Max Act: 3.5896. Min Act: -0.1700

Data Index: 82378 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 3.8713. Min Range: -3.8713

Max Act: 3.5896. Min Act: -0.1700

Data Index: 267945 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 3.8713. Min Range: -3.8713

Max Act: 3.5896. Min Act: -0.1700

Data Index: 1140458 (C4 (Web Text))

Max Activating Token Index: 639

Text #12

Max Range: 3.8713. Min Range: -3.8713

Max Act: 3.5896. Min Act: -0.1700

Data Index: 67819 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 3.8713. Min Range: -3.8713

Max Act: 3.5270. Min Act: -0.1700

Data Index: 999714 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 3.8713. Min Range: -3.8713

Max Act: 3.5583. Min Act: -0.1700

Data Index: 1041778 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 3.8713. Min Range: -3.8713

Max Act: 3.5583. Min Act: -0.1700

Data Index: 581632 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 3.8713. Min Range: -3.8713

Max Act: 3.5583. Min Act: -0.1700

Data Index: 59938 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 3.8713. Min Range: -3.8713

Max Act: 3.5896. Min Act: -0.1700

Data Index: 1140184 (C4 (Web Text))

Max Activating Token Index: 796

Text #18

Max Range: 3.8713. Min Range: -3.8713

Max Act: 3.5583. Min Act: -0.1700

Data Index: 422219 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 3.8713. Min Range: -3.8713

Max Act: 3.5583. Min Act: -0.1700

Data Index: 726822 (C4 (Web Text))

Max Activating Token Index: 466