Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1253 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.2816. Min Act: -0.1700

Data Index: 244082 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.2188. Min Act: -0.1700

Data Index: 315815 (C4 (Web Text))

Max Activating Token Index: 909

Text #2

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.1401. Min Act: -0.1700

Data Index: 1113942 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.1558. Min Act: -0.1700

Data Index: 1015508 (C4 (Web Text))

Max Activating Token Index: 384

Text #4

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.1401. Min Act: -0.1700

Data Index: 834348 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.1401. Min Act: -0.1700

Data Index: 836865 (C4 (Web Text))

Max Activating Token Index: 304

Text #6

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.0928. Min Act: -0.1700

Data Index: 305902 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.1085. Min Act: -0.1700

Data Index: 1439749 (Python Code)

Max Activating Token Index: 494

Text #8

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.0928. Min Act: -0.1700

Data Index: 1413691 (Python Code)

Max Activating Token Index: 273

Text #9

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.1085. Min Act: -0.1700

Data Index: 1353833 (C4 (Web Text))

Max Activating Token Index: 110

Text #10

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.0928. Min Act: -0.1700

Data Index: 1324176 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.0770. Min Act: -0.1700

Data Index: 931509 (C4 (Web Text))

Max Activating Token Index: 592

Text #12

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.0770. Min Act: -0.1700

Data Index: 756323 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.0770. Min Act: -0.1700

Data Index: 214233 (C4 (Web Text))

Max Activating Token Index: 318

Text #14

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.0770. Min Act: -0.1700

Data Index: 404290 (C4 (Web Text))

Max Activating Token Index: 265

Text #15

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.0928. Min Act: -0.1700

Data Index: 782732 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.0612. Min Act: -0.1700

Data Index: 1527068 (Python Code)

Max Activating Token Index: 777

Text #17

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.0454. Min Act: -0.1700

Data Index: 1385557 (Python Code)

Max Activating Token Index: 778

Text #18

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.0612. Min Act: -0.1700

Data Index: 1629783 (Python Code)

Max Activating Token Index: 125

Text #19

Max Range: 3.2816. Min Range: -3.2816

Max Act: 3.0770. Min Act: -0.1700

Data Index: 155538 (C4 (Web Text))

Max Activating Token Index: 191