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

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

Neuron 1851 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.4526. Min Range: -5.4526

Max Act: 5.4526. Min Act: -0.1700

Data Index: 236113 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 5.4526. Min Range: -5.4526

Max Act: 5.1714. Min Act: -0.1700

Data Index: 520677 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 5.4526. Min Range: -5.4526

Max Act: 5.1089. Min Act: -0.1700

Data Index: 749915 (C4 (Web Text))

Max Activating Token Index: 849

Text #3

Max Range: 5.4526. Min Range: -5.4526

Max Act: 5.1089. Min Act: -0.1700

Data Index: 601575 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 5.4526. Min Range: -5.4526

Max Act: 5.1089. Min Act: -0.1700

Data Index: 486708 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 5.4526. Min Range: -5.4526

Max Act: 4.9839. Min Act: -0.1700

Data Index: 469670 (C4 (Web Text))

Max Activating Token Index: 942

Text #6

Max Range: 5.4526. Min Range: -5.4526

Max Act: 4.9526. Min Act: -0.1700

Data Index: 1192679 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 5.4526. Min Range: -5.4526

Max Act: 4.9839. Min Act: -0.1700

Data Index: 550794 (C4 (Web Text))

Max Activating Token Index: 474

Text #8

Max Range: 5.4526. Min Range: -5.4526

Max Act: 4.9526. Min Act: -0.1700

Data Index: 734821 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 5.4526. Min Range: -5.4526

Max Act: 4.9214. Min Act: -0.1700

Data Index: 86932 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 5.4526. Min Range: -5.4526

Max Act: 4.9214. Min Act: -0.1700

Data Index: 245744 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 5.4526. Min Range: -5.4526

Max Act: 4.9526. Min Act: -0.1700

Data Index: 1236058 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 5.4526. Min Range: -5.4526

Max Act: 4.8901. Min Act: -0.1700

Data Index: 713838 (C4 (Web Text))

Max Activating Token Index: 1003

Text #13

Max Range: 5.4526. Min Range: -5.4526

Max Act: 4.9214. Min Act: -0.1700

Data Index: 223908 (C4 (Web Text))

Max Activating Token Index: 206

Text #14

Max Range: 5.4526. Min Range: -5.4526

Max Act: 4.9526. Min Act: -0.1700

Data Index: 498759 (C4 (Web Text))

Max Activating Token Index: 224

Text #15

Max Range: 5.4526. Min Range: -5.4526

Max Act: 4.9214. Min Act: -0.1700

Data Index: 831349 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 5.4526. Min Range: -5.4526

Max Act: 4.8589. Min Act: -0.1700

Data Index: 553357 (C4 (Web Text))

Max Activating Token Index: 160

Text #17

Max Range: 5.4526. Min Range: -5.4526

Max Act: 4.8901. Min Act: -0.1700

Data Index: 41752 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 5.4526. Min Range: -5.4526

Max Act: 4.8901. Min Act: -0.1699

Data Index: 774065 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 5.4526. Min Range: -5.4526

Max Act: 4.8589. Min Act: -0.1700

Data Index: 135544 (C4 (Web Text))

Max Activating Token Index: 912