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

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

Neuron 1734 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: 3.7491. Min Range: -3.7491

Max Act: 3.7491. Min Act: -0.1700

Data Index: 98267 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.6552. Min Act: -0.1700

Data Index: 1070429 (C4 (Web Text))

Max Activating Token Index: 744

Text #2

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.6865. Min Act: -0.1700

Data Index: 346441 (C4 (Web Text))

Max Activating Token Index: 37

Text #3

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.6552. Min Act: -0.1700

Data Index: 771052 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.6552. Min Act: -0.1700

Data Index: 499474 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.6552. Min Act: -0.1700

Data Index: 169867 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.6552. Min Act: -0.1700

Data Index: 667531 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.6239. Min Act: -0.1700

Data Index: 69442 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.6239. Min Act: -0.1700

Data Index: 823041 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.5613. Min Act: -0.1700

Data Index: 913445 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.5456. Min Act: -0.1700

Data Index: 136104 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.5143. Min Act: -0.1700

Data Index: 28684 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.5613. Min Act: -0.1700

Data Index: 1237677 (C4 (Web Text))

Max Activating Token Index: 558

Text #13

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.5926. Min Act: -0.1700

Data Index: 650054 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.5613. Min Act: -0.1700

Data Index: 1046612 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.5143. Min Act: -0.1700

Data Index: 921241 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.5143. Min Act: -0.1700

Data Index: 851433 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.5300. Min Act: -0.1700

Data Index: 84254 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.5143. Min Act: -0.1700

Data Index: 1005011 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 3.7491. Min Range: -3.7491

Max Act: 3.4673. Min Act: -0.1700

Data Index: 494276 (C4 (Web Text))

Max Activating Token Index: 650