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

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

Neuron 1774 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1647. Min Range: -5.1647

Max Act: 5.1647. Min Act: -0.1700

Data Index: 996525 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 5.1647. Min Range: -5.1647

Max Act: 5.0710. Min Act: -0.1700

Data Index: 28358 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 5.1647. Min Range: -5.1647

Max Act: 5.0710. Min Act: -0.1700

Data Index: 569898 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.9772. Min Act: -0.1700

Data Index: 130744 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.9772. Min Act: -0.1700

Data Index: 630702 (C4 (Web Text))

Max Activating Token Index: 70

Text #5

Max Range: 5.1647. Min Range: -5.1647

Max Act: 5.0397. Min Act: -0.1700

Data Index: 1333770 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 5.1647. Min Range: -5.1647

Max Act: 5.0397. Min Act: -0.1700

Data Index: 672598 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.9147. Min Act: -0.1700

Data Index: 260010 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.9460. Min Act: -0.1700

Data Index: 39991 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.9460. Min Act: -0.1700

Data Index: 561256 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.9147. Min Act: -0.1700

Data Index: 788728 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.8835. Min Act: -0.1700

Data Index: 1180055 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.9460. Min Act: -0.1700

Data Index: 376854 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.8522. Min Act: -0.1700

Data Index: 694444 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.9147. Min Act: -0.1700

Data Index: 871311 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.8210. Min Act: -0.1700

Data Index: 1134528 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.8835. Min Act: -0.1700

Data Index: 1251001 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.7897. Min Act: -0.1700

Data Index: 496911 (C4 (Web Text))

Max Activating Token Index: 658

Text #18

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.9147. Min Act: -0.1700

Data Index: 1003097 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 5.1647. Min Range: -5.1647

Max Act: 4.7585. Min Act: -0.1700

Data Index: 366885 (C4 (Web Text))

Max Activating Token Index: 747