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

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

Neuron 1901 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.7629. Min Range: -3.7629

Max Act: 3.7629. Min Act: -0.1700

Data Index: 270336 (C4 (Web Text))

Max Activating Token Index: 702

Text #1

Max Range: 3.7629. Min Range: -3.7629

Max Act: 3.7629. Min Act: -0.1700

Data Index: 792931 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 3.7629. Min Range: -3.7629

Max Act: 3.7316. Min Act: -0.1700

Data Index: 1258678 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 3.7629. Min Range: -3.7629

Max Act: 3.6846. Min Act: -0.1700

Data Index: 364680 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 3.7629. Min Range: -3.7629

Max Act: 3.6690. Min Act: -0.1700

Data Index: 1352234 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 3.7629. Min Range: -3.7629

Max Act: 3.6846. Min Act: -0.1700

Data Index: 360547 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 3.7629. Min Range: -3.7629

Max Act: 3.6220. Min Act: -0.1700

Data Index: 474747 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 3.7629. Min Range: -3.7629

Max Act: 3.6846. Min Act: -0.1700

Data Index: 988915 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 3.7629. Min Range: -3.7629

Max Act: 3.6533. Min Act: -0.1700

Data Index: 990661 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 3.7629. Min Range: -3.7629

Max Act: 3.6064. Min Act: -0.1700

Data Index: 1312427 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 3.7629. Min Range: -3.7629

Max Act: 3.6064. Min Act: -0.1700

Data Index: 938221 (C4 (Web Text))

Max Activating Token Index: 701

Text #11

Max Range: 3.7629. Min Range: -3.7629

Max Act: 3.6220. Min Act: -0.1700

Data Index: 174488 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 3.7629. Min Range: -3.7629

Max Act: 3.5281. Min Act: -0.1700

Data Index: 641332 (C4 (Web Text))

Max Activating Token Index: 277

Text #13

Max Range: 3.7629. Min Range: -3.7629

Max Act: 3.6064. Min Act: -0.1700

Data Index: 346066 (C4 (Web Text))

Max Activating Token Index: 579

Text #14

Max Range: 3.7629. Min Range: -3.7629

Max Act: 3.4811. Min Act: -0.1700

Data Index: 550414 (C4 (Web Text))

Max Activating Token Index: 326

Text #15

Max Range: 3.7629. Min Range: -3.7629

Max Act: 3.4811. Min Act: -0.1700

Data Index: 601205 (C4 (Web Text))

Max Activating Token Index: 989

Text #16

Max Range: 3.7629. Min Range: -3.7629

Max Act: 3.4811. Min Act: -0.1700

Data Index: 465854 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 3.7629. Min Range: -3.7629

Max Act: 3.4497. Min Act: -0.1700

Data Index: 34852 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 3.7629. Min Range: -3.7629

Max Act: 3.4184. Min Act: -0.1700

Data Index: 652334 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 3.7629. Min Range: -3.7629

Max Act: 3.3713. Min Act: -0.1700

Data Index: 609274 (C4 (Web Text))

Max Activating Token Index: 838