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

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

Neuron 702 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5014. Min Range: -5.5014

Max Act: 5.4389. Min Act: -0.1700

Data Index: 356830 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 5.5014. Min Range: -5.5014

Max Act: 5.5014. Min Act: -0.1700

Data Index: 764439 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 5.5014. Min Range: -5.5014

Max Act: 5.5014. Min Act: -0.1700

Data Index: 405258 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 5.5014. Min Range: -5.5014

Max Act: 5.4077. Min Act: -0.1700

Data Index: 212517 (C4 (Web Text))

Max Activating Token Index: 345

Text #4

Max Range: 5.5014. Min Range: -5.5014

Max Act: 5.3452. Min Act: -0.1700

Data Index: 92302 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 5.5014. Min Range: -5.5014

Max Act: 5.3764. Min Act: -0.1700

Data Index: 1021091 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 5.5014. Min Range: -5.5014

Max Act: 5.4389. Min Act: -0.1700

Data Index: 220119 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 5.5014. Min Range: -5.5014

Max Act: 5.3452. Min Act: -0.1700

Data Index: 1518915 (Python Code)

Max Activating Token Index: 94

Text #8

Max Range: 5.5014. Min Range: -5.5014

Max Act: 5.4077. Min Act: -0.1700

Data Index: 853268 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 5.5014. Min Range: -5.5014

Max Act: 5.3764. Min Act: -0.1700

Data Index: 500960 (C4 (Web Text))

Max Activating Token Index: 123

Text #10

Max Range: 5.5014. Min Range: -5.5014

Max Act: 5.4077. Min Act: -0.1700

Data Index: 213664 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 5.5014. Min Range: -5.5014

Max Act: 5.3452. Min Act: -0.1700

Data Index: 1232108 (C4 (Web Text))

Max Activating Token Index: 110

Text #12

Max Range: 5.5014. Min Range: -5.5014

Max Act: 5.4389. Min Act: -0.1700

Data Index: 107990 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 5.5014. Min Range: -5.5014

Max Act: 5.4389. Min Act: -0.1700

Data Index: 189923 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 5.5014. Min Range: -5.5014

Max Act: 5.4389. Min Act: -0.1700

Data Index: 1016736 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 5.5014. Min Range: -5.5014

Max Act: 5.3452. Min Act: -0.1700

Data Index: 667032 (C4 (Web Text))

Max Activating Token Index: 986

Text #16

Max Range: 5.5014. Min Range: -5.5014

Max Act: 5.4077. Min Act: -0.1700

Data Index: 1217463 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 5.5014. Min Range: -5.5014

Max Act: 5.4077. Min Act: -0.1700

Data Index: 685655 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 5.5014. Min Range: -5.5014

Max Act: 5.4077. Min Act: -0.1700

Data Index: 918403 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 5.5014. Min Range: -5.5014

Max Act: 5.3764. Min Act: -0.1700

Data Index: 79153 (C4 (Web Text))

Max Activating Token Index: 639