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

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

Neuron 391 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: 3.1915. Min Range: -3.1915

Max Act: 3.1915. Min Act: -0.1700

Data Index: 252753 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 3.1915. Min Range: -3.1915

Max Act: 3.1600. Min Act: -0.1700

Data Index: 1219787 (C4 (Web Text))

Max Activating Token Index: 988

Text #2

Max Range: 3.1915. Min Range: -3.1915

Max Act: 3.1600. Min Act: -0.1700

Data Index: 515152 (C4 (Web Text))

Max Activating Token Index: 739

Text #3

Max Range: 3.1915. Min Range: -3.1915

Max Act: 3.1285. Min Act: -0.1700

Data Index: 1346155 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 3.1915. Min Range: -3.1915

Max Act: 3.1442. Min Act: -0.1700

Data Index: 220031 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 3.1915. Min Range: -3.1915

Max Act: 3.0812. Min Act: -0.1700

Data Index: 1053019 (C4 (Web Text))

Max Activating Token Index: 411

Text #6

Max Range: 3.1915. Min Range: -3.1915

Max Act: 3.1127. Min Act: -0.1700

Data Index: 599686 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 3.1915. Min Range: -3.1915

Max Act: 3.0812. Min Act: -0.1700

Data Index: 912246 (C4 (Web Text))

Max Activating Token Index: 605

Text #8

Max Range: 3.1915. Min Range: -3.1915

Max Act: 3.1127. Min Act: -0.1700

Data Index: 475263 (C4 (Web Text))

Max Activating Token Index: 795

Text #9

Max Range: 3.1915. Min Range: -3.1915

Max Act: 3.0969. Min Act: -0.1700

Data Index: 424936 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 3.1915. Min Range: -3.1915

Max Act: 3.0812. Min Act: -0.1700

Data Index: 1046184 (C4 (Web Text))

Max Activating Token Index: 539

Text #11

Max Range: 3.1915. Min Range: -3.1915

Max Act: 3.0812. Min Act: -0.1700

Data Index: 1020663 (C4 (Web Text))

Max Activating Token Index: 262

Text #12

Max Range: 3.1915. Min Range: -3.1915

Max Act: 3.0654. Min Act: -0.1700

Data Index: 160974 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 3.1915. Min Range: -3.1915

Max Act: 3.0654. Min Act: -0.1700

Data Index: 578332 (C4 (Web Text))

Max Activating Token Index: 750

Text #14

Max Range: 3.1915. Min Range: -3.1915

Max Act: 3.0338. Min Act: -0.1700

Data Index: 721188 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 3.1915. Min Range: -3.1915

Max Act: 3.0496. Min Act: -0.1700

Data Index: 248513 (C4 (Web Text))

Max Activating Token Index: 531

Text #16

Max Range: 3.1915. Min Range: -3.1915

Max Act: 3.0338. Min Act: -0.1700

Data Index: 298867 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 3.1915. Min Range: -3.1915

Max Act: 3.0654. Min Act: -0.1700

Data Index: 536558 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 3.1915. Min Range: -3.1915

Max Act: 3.0180. Min Act: -0.1700

Data Index: 772120 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 3.1915. Min Range: -3.1915

Max Act: 3.0338. Min Act: -0.1700

Data Index: 1327611 (C4 (Web Text))

Max Activating Token Index: 607