Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1635 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 7.9928. Min Range: -7.9928

Max Act: 7.9928. Min Act: -0.1699

Data Index: 695392 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 7.9928. Min Range: -7.9928

Max Act: 7.8678. Min Act: -0.1700

Data Index: 280337 (C4 (Web Text))

Max Activating Token Index: 199

Text #2

Max Range: 7.9928. Min Range: -7.9928

Max Act: 7.8053. Min Act: -0.1699

Data Index: 737283 (C4 (Web Text))

Max Activating Token Index: 178

Text #3

Max Range: 7.9928. Min Range: -7.9928

Max Act: 7.7428. Min Act: -0.1700

Data Index: 44074 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 7.9928. Min Range: -7.9928

Max Act: 7.7428. Min Act: -0.1700

Data Index: 127917 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 7.9928. Min Range: -7.9928

Max Act: 7.6803. Min Act: -0.1700

Data Index: 776073 (C4 (Web Text))

Max Activating Token Index: 85

Text #6

Max Range: 7.9928. Min Range: -7.9928

Max Act: 7.6178. Min Act: -0.1700

Data Index: 818929 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 7.9928. Min Range: -7.9928

Max Act: 7.6178. Min Act: -0.1700

Data Index: 51870 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 7.9928. Min Range: -7.9928

Max Act: 7.7115. Min Act: -0.1700

Data Index: 444686 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 7.9928. Min Range: -7.9928

Max Act: 7.6178. Min Act: -0.1700

Data Index: 377125 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 7.9928. Min Range: -7.9928

Max Act: 7.5865. Min Act: -0.1700

Data Index: 186940 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 7.9928. Min Range: -7.9928

Max Act: 7.5865. Min Act: -0.1700

Data Index: 784454 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 7.9928. Min Range: -7.9928

Max Act: 7.4928. Min Act: -0.1700

Data Index: 929012 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 7.9928. Min Range: -7.9928

Max Act: 7.5553. Min Act: -0.1700

Data Index: 330917 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 7.9928. Min Range: -7.9928

Max Act: 7.5240. Min Act: -0.1700

Data Index: 544352 (C4 (Web Text))

Max Activating Token Index: 789

Text #15

Max Range: 7.9928. Min Range: -7.9928

Max Act: 7.4615. Min Act: -0.1700

Data Index: 1098939 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 7.9928. Min Range: -7.9928

Max Act: 7.4928. Min Act: -0.1700

Data Index: 235259 (C4 (Web Text))

Max Activating Token Index: 231

Text #17

Max Range: 7.9928. Min Range: -7.9928

Max Act: 7.4615. Min Act: -0.1699

Data Index: 91066 (C4 (Web Text))

Max Activating Token Index: 279

Text #18

Max Range: 7.9928. Min Range: -7.9928

Max Act: 7.4615. Min Act: -0.1698

Data Index: 62302 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 7.9928. Min Range: -7.9928

Max Act: 7.3990. Min Act: -0.1700

Data Index: 1094322 (C4 (Web Text))

Max Activating Token Index: 85