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

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

Neuron 796 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: 4.3040. Min Range: -4.3040

Max Act: 4.3040. Min Act: -0.1700

Data Index: 850523 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 4.3040. Min Range: -4.3040

Max Act: 4.1427. Min Act: -0.1700

Data Index: 1177843 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 4.3040. Min Range: -4.3040

Max Act: 4.0748. Min Act: -0.1700

Data Index: 1428476 (Python Code)

Max Activating Token Index: 579

Text #3

Max Range: 4.3040. Min Range: -4.3040

Max Act: 4.0253. Min Act: -0.1700

Data Index: 1391917 (Python Code)

Max Activating Token Index: 719

Text #4

Max Range: 4.3040. Min Range: -4.3040

Max Act: 4.0247. Min Act: -0.1700

Data Index: 1066662 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 4.3040. Min Range: -4.3040

Max Act: 4.0026. Min Act: -0.1700

Data Index: 1162922 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 4.3040. Min Range: -4.3040

Max Act: 3.9996. Min Act: -0.1700

Data Index: 1372435 (Python Code)

Max Activating Token Index: 45

Text #7

Max Range: 4.3040. Min Range: -4.3040

Max Act: 3.9757. Min Act: -0.1700

Data Index: 868292 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 4.3040. Min Range: -4.3040

Max Act: 3.9627. Min Act: -0.1700

Data Index: 1389767 (Python Code)

Max Activating Token Index: 804

Text #9

Max Range: 4.3040. Min Range: -4.3040

Max Act: 3.9562. Min Act: -0.1700

Data Index: 1316251 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 4.3040. Min Range: -4.3040

Max Act: 3.8975. Min Act: -0.1700

Data Index: 771173 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 4.3040. Min Range: -4.3040

Max Act: 3.9399. Min Act: -0.1700

Data Index: 171536 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 4.3040. Min Range: -4.3040

Max Act: 3.9221. Min Act: -0.1700

Data Index: 1228386 (C4 (Web Text))

Max Activating Token Index: 757

Text #13

Max Range: 4.3040. Min Range: -4.3040

Max Act: 3.9061. Min Act: -0.1700

Data Index: 206142 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 4.3040. Min Range: -4.3040

Max Act: 3.8718. Min Act: -0.1700

Data Index: 1635772 (Python Code)

Max Activating Token Index: 964

Text #15

Max Range: 4.3040. Min Range: -4.3040

Max Act: 3.8889. Min Act: -0.1700

Data Index: 162711 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 4.3040. Min Range: -4.3040

Max Act: 3.8670. Min Act: -0.1700

Data Index: 212360 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 4.3040. Min Range: -4.3040

Max Act: 3.8798. Min Act: -0.1700

Data Index: 190810 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 4.3040. Min Range: -4.3040

Max Act: 3.8691. Min Act: -0.1700

Data Index: 646256 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 4.3040. Min Range: -4.3040

Max Act: 3.8015. Min Act: -0.1700

Data Index: 312094 (C4 (Web Text))

Max Activating Token Index: 957