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

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

Neuron 697 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3600. Min Range: -5.3600

Max Act: 5.3600. Min Act: -0.1700

Data Index: 1526677 (Python Code)

Max Activating Token Index: 1003

Text #1

Max Range: 5.3600. Min Range: -5.3600

Max Act: 5.1100. Min Act: -0.1700

Data Index: 234612 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 5.3600. Min Range: -5.3600

Max Act: 5.0162. Min Act: -0.1700

Data Index: 1342973 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 5.3600. Min Range: -5.3600

Max Act: 5.0475. Min Act: -0.1700

Data Index: 784970 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 5.3600. Min Range: -5.3600

Max Act: 4.9537. Min Act: -0.1700

Data Index: 244798 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 5.3600. Min Range: -5.3600

Max Act: 4.9537. Min Act: -0.1700

Data Index: 22099 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 5.3600. Min Range: -5.3600

Max Act: 4.9537. Min Act: -0.1700

Data Index: 1150164 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 5.3600. Min Range: -5.3600

Max Act: 4.9537. Min Act: -0.1700

Data Index: 656633 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 5.3600. Min Range: -5.3600

Max Act: 4.8912. Min Act: -0.1700

Data Index: 782097 (C4 (Web Text))

Max Activating Token Index: 486

Text #9

Max Range: 5.3600. Min Range: -5.3600

Max Act: 4.9225. Min Act: -0.1700

Data Index: 1357719 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 5.3600. Min Range: -5.3600

Max Act: 4.9225. Min Act: -0.1700

Data Index: 1302807 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 5.3600. Min Range: -5.3600

Max Act: 4.8912. Min Act: -0.1700

Data Index: 471505 (C4 (Web Text))

Max Activating Token Index: 464

Text #12

Max Range: 5.3600. Min Range: -5.3600

Max Act: 4.8600. Min Act: -0.1700

Data Index: 1144598 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 5.3600. Min Range: -5.3600

Max Act: 4.8912. Min Act: -0.1700

Data Index: 1012124 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 5.3600. Min Range: -5.3600

Max Act: 4.8912. Min Act: -0.1700

Data Index: 98621 (C4 (Web Text))

Max Activating Token Index: 202

Text #15

Max Range: 5.3600. Min Range: -5.3600

Max Act: 4.8287. Min Act: -0.1700

Data Index: 764606 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 5.3600. Min Range: -5.3600

Max Act: 4.8600. Min Act: -0.1700

Data Index: 543832 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 5.3600. Min Range: -5.3600

Max Act: 4.8600. Min Act: -0.1700

Data Index: 714083 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 5.3600. Min Range: -5.3600

Max Act: 4.8600. Min Act: -0.1700

Data Index: 1206014 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 5.3600. Min Range: -5.3600

Max Act: 4.7975. Min Act: -0.1700

Data Index: 553212 (C4 (Web Text))

Max Activating Token Index: 846