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

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

Neuron 370 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.3882. Min Act: -0.1700

Data Index: 1050148 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.3882. Min Act: -0.1700

Data Index: 1260300 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.3725. Min Act: -0.1700

Data Index: 797083 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.3568. Min Act: -0.1700

Data Index: 588544 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.3725. Min Act: -0.1700

Data Index: 597498 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.3411. Min Act: -0.1700

Data Index: 902614 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.3725. Min Act: -0.1700

Data Index: 1314009 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.3411. Min Act: -0.1700

Data Index: 263535 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.3411. Min Act: -0.1700

Data Index: 1231896 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.3568. Min Act: -0.1700

Data Index: 55882 (C4 (Web Text))

Max Activating Token Index: 984

Text #10

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.3568. Min Act: -0.1700

Data Index: 979879 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.3411. Min Act: -0.1700

Data Index: 1028016 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.3411. Min Act: -0.1700

Data Index: 1083270 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.3411. Min Act: -0.1700

Data Index: 1113564 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.3254. Min Act: -0.1700

Data Index: 1181489 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.3254. Min Act: -0.1700

Data Index: 71699 (C4 (Web Text))

Max Activating Token Index: 577

Text #16

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.3097. Min Act: -0.1700

Data Index: 777999 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.3254. Min Act: -0.1700

Data Index: 44583 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.3097. Min Act: -0.1700

Data Index: 273986 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 3.3882. Min Range: -3.3882

Max Act: 3.3254. Min Act: -0.1700

Data Index: 924165 (C4 (Web Text))

Max Activating Token Index: 425