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

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

Neuron 1687 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.4478. Min Act: -0.1700

Data Index: 902159 (C4 (Web Text))

Max Activating Token Index: 799

Text #1

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.3851. Min Act: -0.1700

Data Index: 491185 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.3694. Min Act: -0.1700

Data Index: 863735 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.3223. Min Act: -0.1700

Data Index: 923606 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.3223. Min Act: -0.1700

Data Index: 1046478 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.2909. Min Act: -0.1700

Data Index: 665954 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.2909. Min Act: -0.1700

Data Index: 1000107 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.2752. Min Act: -0.1700

Data Index: 1311828 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.2752. Min Act: -0.1700

Data Index: 420924 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.2752. Min Act: -0.1700

Data Index: 319808 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.2752. Min Act: -0.1700

Data Index: 89612 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.2752. Min Act: -0.1700

Data Index: 714970 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.2752. Min Act: -0.1700

Data Index: 1154153 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.2595. Min Act: -0.1700

Data Index: 601076 (C4 (Web Text))

Max Activating Token Index: 573

Text #14

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.2595. Min Act: -0.1700

Data Index: 1003709 (C4 (Web Text))

Max Activating Token Index: 276

Text #15

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.2595. Min Act: -0.1700

Data Index: 874660 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.2595. Min Act: -0.1700

Data Index: 829785 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.2752. Min Act: -0.1700

Data Index: 727278 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.2595. Min Act: -0.1700

Data Index: 92441 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 3.4478. Min Range: -3.4478

Max Act: 3.2438. Min Act: -0.1700

Data Index: 130384 (C4 (Web Text))

Max Activating Token Index: 434