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

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

Neuron 1742 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: 3.2797. Min Range: -3.2797

Max Act: 3.2797. Min Act: -0.1700

Data Index: 1591154 (Python Code)

Max Activating Token Index: 100

Text #1

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.1288. Min Act: -0.1700

Data Index: 1642916 (Python Code)

Max Activating Token Index: 978

Text #2

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.0914. Min Act: -0.1700

Data Index: 87148 (C4 (Web Text))

Max Activating Token Index: 512

Text #3

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.0988. Min Act: -0.1700

Data Index: 665653 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.0645. Min Act: -0.1700

Data Index: 1486990 (Python Code)

Max Activating Token Index: 816

Text #5

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.0608. Min Act: -0.1700

Data Index: 842464 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.0415. Min Act: -0.1700

Data Index: 1569400 (Python Code)

Max Activating Token Index: 9

Text #7

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.0311. Min Act: -0.1700

Data Index: 910975 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.0224. Min Act: -0.1700

Data Index: 1604830 (Python Code)

Max Activating Token Index: 579

Text #9

Max Range: 3.2797. Min Range: -3.2797

Max Act: 3.0097. Min Act: -0.1700

Data Index: 61856 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 3.2797. Min Range: -3.2797

Max Act: 2.9877. Min Act: -0.1700

Data Index: 1650909 (Python Code)

Max Activating Token Index: 13

Text #11

Max Range: 3.2797. Min Range: -3.2797

Max Act: 2.9678. Min Act: -0.1700

Data Index: 1362909 (Python Code)

Max Activating Token Index: 93

Text #12

Max Range: 3.2797. Min Range: -3.2797

Max Act: 2.9791. Min Act: -0.1699

Data Index: 926754 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 3.2797. Min Range: -3.2797

Max Act: 2.9704. Min Act: -0.1699

Data Index: 615599 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 3.2797. Min Range: -3.2797

Max Act: 2.9759. Min Act: -0.1699

Data Index: 1072839 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 3.2797. Min Range: -3.2797

Max Act: 2.9726. Min Act: -0.1700

Data Index: 616978 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 3.2797. Min Range: -3.2797

Max Act: 2.9643. Min Act: -0.1700

Data Index: 1561268 (Python Code)

Max Activating Token Index: 853

Text #17

Max Range: 3.2797. Min Range: -3.2797

Max Act: 2.9689. Min Act: -0.1700

Data Index: 636572 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 3.2797. Min Range: -3.2797

Max Act: 2.9484. Min Act: -0.1700

Data Index: 214923 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 3.2797. Min Range: -3.2797

Max Act: 2.9436. Min Act: -0.1700

Data Index: 1620386 (Python Code)

Max Activating Token Index: 504