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

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

Neuron 1940 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3816. Min Range: -3.3816

Max Act: 3.3816. Min Act: -0.1700

Data Index: 1056356 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 3.3816. Min Range: -3.3816

Max Act: 3.3816. Min Act: -0.1700

Data Index: 1352458 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 3.3816. Min Range: -3.3816

Max Act: 3.3188. Min Act: -0.1700

Data Index: 948439 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 3.3816. Min Range: -3.3816

Max Act: 3.3031. Min Act: -0.1700

Data Index: 685757 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 3.3816. Min Range: -3.3816

Max Act: 3.2874. Min Act: -0.1700

Data Index: 10420 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 3.3816. Min Range: -3.3816

Max Act: 3.2717. Min Act: -0.1700

Data Index: 941615 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 3.3816. Min Range: -3.3816

Max Act: 3.2717. Min Act: -0.1700

Data Index: 92993 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 3.3816. Min Range: -3.3816

Max Act: 3.2246. Min Act: -0.1700

Data Index: 179212 (C4 (Web Text))

Max Activating Token Index: 727

Text #8

Max Range: 3.3816. Min Range: -3.3816

Max Act: 3.2088. Min Act: -0.1700

Data Index: 232635 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 3.3816. Min Range: -3.3816

Max Act: 3.2246. Min Act: -0.1700

Data Index: 434499 (C4 (Web Text))

Max Activating Token Index: 742

Text #10

Max Range: 3.3816. Min Range: -3.3816

Max Act: 3.1931. Min Act: -0.1700

Data Index: 1141904 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 3.3816. Min Range: -3.3816

Max Act: 3.1774. Min Act: -0.1700

Data Index: 230253 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 3.3816. Min Range: -3.3816

Max Act: 3.1931. Min Act: -0.1700

Data Index: 1122642 (C4 (Web Text))

Max Activating Token Index: 33

Text #13

Max Range: 3.3816. Min Range: -3.3816

Max Act: 3.1931. Min Act: -0.1700

Data Index: 49439 (C4 (Web Text))

Max Activating Token Index: 899

Text #14

Max Range: 3.3816. Min Range: -3.3816

Max Act: 3.1931. Min Act: -0.1700

Data Index: 517127 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 3.3816. Min Range: -3.3816

Max Act: 3.1931. Min Act: -0.1700

Data Index: 1043560 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 3.3816. Min Range: -3.3816

Max Act: 3.1774. Min Act: -0.1700

Data Index: 590539 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 3.3816. Min Range: -3.3816

Max Act: 3.1616. Min Act: -0.1700

Data Index: 477536 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 3.3816. Min Range: -3.3816

Max Act: 3.1931. Min Act: -0.1700

Data Index: 738381 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 3.3816. Min Range: -3.3816

Max Act: 3.1774. Min Act: -0.1700

Data Index: 48614 (C4 (Web Text))

Max Activating Token Index: 572