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

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

Neuron 900 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.2915. Min Act: -0.1700

Data Index: 348926 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1185. Min Act: -0.1700

Data Index: 454495 (C4 (Web Text))

Max Activating Token Index: 121

Text #2

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.1027. Min Act: -0.1700

Data Index: 1273774 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.0869. Min Act: -0.1700

Data Index: 759427 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.0869. Min Act: -0.1700

Data Index: 896299 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.0712. Min Act: -0.1700

Data Index: 1059735 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.0554. Min Act: -0.1700

Data Index: 592475 (C4 (Web Text))

Max Activating Token Index: 368

Text #7

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.0396. Min Act: -0.1700

Data Index: 845316 (C4 (Web Text))

Max Activating Token Index: 878

Text #8

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.0554. Min Act: -0.1700

Data Index: 130454 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.0238. Min Act: -0.1700

Data Index: 22874 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.0554. Min Act: -0.1700

Data Index: 567584 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.0238. Min Act: -0.1700

Data Index: 682861 (C4 (Web Text))

Max Activating Token Index: 253

Text #12

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.0238. Min Act: -0.1700

Data Index: 1328383 (C4 (Web Text))

Max Activating Token Index: 573

Text #13

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.0396. Min Act: -0.1700

Data Index: 1237874 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.0080. Min Act: -0.1700

Data Index: 176767 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.0080. Min Act: -0.1700

Data Index: 1139914 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.0080. Min Act: -0.1700

Data Index: 215555 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 3.2915. Min Range: -3.2915

Max Act: 2.9764. Min Act: -0.1700

Data Index: 23558 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 3.2915. Min Range: -3.2915

Max Act: 2.9922. Min Act: -0.1700

Data Index: 593450 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 3.2915. Min Range: -3.2915

Max Act: 3.0080. Min Act: -0.1700

Data Index: 221459 (C4 (Web Text))

Max Activating Token Index: 688