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

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

Neuron 1792 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: 3.3112. Min Range: -3.3112

Max Act: 3.3112. Min Act: -0.1700

Data Index: 749521 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 3.3112. Min Range: -3.3112

Max Act: 3.2484. Min Act: -0.1700

Data Index: 482647 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 3.3112. Min Range: -3.3112

Max Act: 3.2169. Min Act: -0.1700

Data Index: 1285749 (C4 (Web Text))

Max Activating Token Index: 391

Text #3

Max Range: 3.3112. Min Range: -3.3112

Max Act: 3.1855. Min Act: -0.1700

Data Index: 446668 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 3.3112. Min Range: -3.3112

Max Act: 3.1697. Min Act: -0.1700

Data Index: 1316164 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 3.3112. Min Range: -3.3112

Max Act: 3.1697. Min Act: -0.1700

Data Index: 1287463 (C4 (Web Text))

Max Activating Token Index: 118

Text #6

Max Range: 3.3112. Min Range: -3.3112

Max Act: 3.1697. Min Act: -0.1700

Data Index: 1107538 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 3.3112. Min Range: -3.3112

Max Act: 3.1697. Min Act: -0.1700

Data Index: 964655 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 3.3112. Min Range: -3.3112

Max Act: 3.1382. Min Act: -0.1700

Data Index: 355447 (C4 (Web Text))

Max Activating Token Index: 659

Text #9

Max Range: 3.3112. Min Range: -3.3112

Max Act: 3.1540. Min Act: -0.1700

Data Index: 549902 (C4 (Web Text))

Max Activating Token Index: 673

Text #10

Max Range: 3.3112. Min Range: -3.3112

Max Act: 3.1067. Min Act: -0.1700

Data Index: 843030 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 3.3112. Min Range: -3.3112

Max Act: 3.1067. Min Act: -0.1700

Data Index: 217967 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 3.3112. Min Range: -3.3112

Max Act: 3.1067. Min Act: -0.1700

Data Index: 997995 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 3.3112. Min Range: -3.3112

Max Act: 3.0909. Min Act: -0.1700

Data Index: 448774 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 3.3112. Min Range: -3.3112

Max Act: 3.0909. Min Act: -0.1700

Data Index: 1088597 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 3.3112. Min Range: -3.3112

Max Act: 3.0752. Min Act: -0.1700

Data Index: 770793 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 3.3112. Min Range: -3.3112

Max Act: 3.0436. Min Act: -0.1700

Data Index: 85155 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 3.3112. Min Range: -3.3112

Max Act: 3.0752. Min Act: -0.1700

Data Index: 499245 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 3.3112. Min Range: -3.3112

Max Act: 3.0909. Min Act: -0.1700

Data Index: 233963 (C4 (Web Text))

Max Activating Token Index: 758

Text #19

Max Range: 3.3112. Min Range: -3.3112

Max Act: 3.0278. Min Act: -0.1700

Data Index: 229887 (C4 (Web Text))

Max Activating Token Index: 795