Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1636 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.2550. Min Range: -3.2550

Max Act: 3.2525. Min Act: -0.1700

Data Index: 1376287 (Python Code)

Max Activating Token Index: 767

Text #1

Max Range: 3.2550. Min Range: -3.2550

Max Act: 3.2550. Min Act: -0.1700

Data Index: 1361892 (Python Code)

Max Activating Token Index: 98

Text #2

Max Range: 3.2550. Min Range: -3.2550

Max Act: 3.2103. Min Act: -0.1699

Data Index: 1522731 (Python Code)

Max Activating Token Index: 127

Text #3

Max Range: 3.2550. Min Range: -3.2550

Max Act: 3.2110. Min Act: -0.1699

Data Index: 1407763 (Python Code)

Max Activating Token Index: 583

Text #4

Max Range: 3.2550. Min Range: -3.2550

Max Act: 3.1770. Min Act: -0.1700

Data Index: 1314773 (C4 (Web Text))

Max Activating Token Index: 362

Text #5

Max Range: 3.2550. Min Range: -3.2550

Max Act: 3.1879. Min Act: -0.1694

Data Index: 1557792 (Python Code)

Max Activating Token Index: 431

Text #6

Max Range: 3.2550. Min Range: -3.2550

Max Act: 3.1988. Min Act: -0.1700

Data Index: 1419970 (Python Code)

Max Activating Token Index: 811

Text #7

Max Range: 3.2550. Min Range: -3.2550

Max Act: 3.1603. Min Act: -0.1700

Data Index: 1521190 (Python Code)

Max Activating Token Index: 704

Text #8

Max Range: 3.2550. Min Range: -3.2550

Max Act: 3.1025. Min Act: -0.1700

Data Index: 1501180 (Python Code)

Max Activating Token Index: 97

Text #9

Max Range: 3.2550. Min Range: -3.2550

Max Act: 3.1063. Min Act: -0.1700

Data Index: 1419956 (Python Code)

Max Activating Token Index: 629

Text #10

Max Range: 3.2550. Min Range: -3.2550

Max Act: 3.1065. Min Act: -0.1700

Data Index: 1546039 (Python Code)

Max Activating Token Index: 954

Text #11

Max Range: 3.2550. Min Range: -3.2550

Max Act: 3.0887. Min Act: -0.1694

Data Index: 1441692 (Python Code)

Max Activating Token Index: 217

Text #12

Max Range: 3.2550. Min Range: -3.2550

Max Act: 3.0734. Min Act: -0.1700

Data Index: 810006 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 3.2550. Min Range: -3.2550

Max Act: 3.0696. Min Act: -0.1700

Data Index: 1651834 (Python Code)

Max Activating Token Index: 282

Text #14

Max Range: 3.2550. Min Range: -3.2550

Max Act: 3.0781. Min Act: -0.1699

Data Index: 1586783 (Python Code)

Max Activating Token Index: 1005

Text #15

Max Range: 3.2550. Min Range: -3.2550

Max Act: 3.0640. Min Act: -0.1699

Data Index: 1387123 (Python Code)

Max Activating Token Index: 995

Text #16

Max Range: 3.2550. Min Range: -3.2550

Max Act: 3.0554. Min Act: -0.1700

Data Index: 1611378 (Python Code)

Max Activating Token Index: 529

Text #17

Max Range: 3.2550. Min Range: -3.2550

Max Act: 3.0374. Min Act: -0.1700

Data Index: 1546626 (Python Code)

Max Activating Token Index: 977

Text #18

Max Range: 3.2550. Min Range: -3.2550

Max Act: 3.0389. Min Act: -0.1700

Data Index: 1412573 (Python Code)

Max Activating Token Index: 467

Text #19

Max Range: 3.2550. Min Range: -3.2550

Max Act: 3.0408. Min Act: -0.1700

Data Index: 1497552 (Python Code)

Max Activating Token Index: 723