Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 148 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9971. Min Range: -3.9971

Max Act: 3.9971. Min Act: -0.1700

Data Index: 290898 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 3.9971. Min Range: -3.9971

Max Act: 3.9659. Min Act: -0.1700

Data Index: 1115320 (C4 (Web Text))

Max Activating Token Index: 17

Text #2

Max Range: 3.9971. Min Range: -3.9971

Max Act: 3.9346. Min Act: -0.1700

Data Index: 850956 (C4 (Web Text))

Max Activating Token Index: 743

Text #3

Max Range: 3.9971. Min Range: -3.9971

Max Act: 3.8721. Min Act: -0.1700

Data Index: 519767 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 3.9971. Min Range: -3.9971

Max Act: 3.8721. Min Act: -0.1700

Data Index: 957068 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 3.9971. Min Range: -3.9971

Max Act: 3.8095. Min Act: -0.1700

Data Index: 1267020 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 3.9971. Min Range: -3.9971

Max Act: 3.7782. Min Act: -0.1700

Data Index: 208416 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 3.9971. Min Range: -3.9971

Max Act: 3.7782. Min Act: -0.1700

Data Index: 497855 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 3.9971. Min Range: -3.9971

Max Act: 3.7156. Min Act: -0.1700

Data Index: 1279546 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 3.9971. Min Range: -3.9971

Max Act: 3.8095. Min Act: -0.1700

Data Index: 87941 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 3.9971. Min Range: -3.9971

Max Act: 3.7782. Min Act: -0.1700

Data Index: 1273753 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 3.9971. Min Range: -3.9971

Max Act: 3.8095. Min Act: -0.1700

Data Index: 739274 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 3.9971. Min Range: -3.9971

Max Act: 3.7469. Min Act: -0.1700

Data Index: 940904 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 3.9971. Min Range: -3.9971

Max Act: 3.7156. Min Act: -0.1700

Data Index: 749039 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 3.9971. Min Range: -3.9971

Max Act: 3.7469. Min Act: -0.1700

Data Index: 1145689 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 3.9971. Min Range: -3.9971

Max Act: 3.7156. Min Act: -0.1700

Data Index: 675014 (C4 (Web Text))

Max Activating Token Index: 865

Text #16

Max Range: 3.9971. Min Range: -3.9971

Max Act: 3.7469. Min Act: -0.1700

Data Index: 151256 (C4 (Web Text))

Max Activating Token Index: 904

Text #17

Max Range: 3.9971. Min Range: -3.9971

Max Act: 3.7469. Min Act: -0.1700

Data Index: 287418 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 3.9971. Min Range: -3.9971

Max Act: 3.7156. Min Act: -0.1700

Data Index: 1032230 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 3.9971. Min Range: -3.9971

Max Act: 3.7156. Min Act: -0.1700

Data Index: 435192 (C4 (Web Text))

Max Activating Token Index: 161