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

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

Neuron 945 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.9789. Min Range: -7.9789

Max Act: 7.9789. Min Act: -0.1700

Data Index: 849374 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 7.9789. Min Range: -7.9789

Max Act: 7.8852. Min Act: -0.1700

Data Index: 578769 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 7.9789. Min Range: -7.9789

Max Act: 7.8227. Min Act: -0.1699

Data Index: 452568 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 7.9789. Min Range: -7.9789

Max Act: 7.7914. Min Act: -0.1700

Data Index: 1203113 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 7.9789. Min Range: -7.9789

Max Act: 7.7602. Min Act: -0.1700

Data Index: 189748 (C4 (Web Text))

Max Activating Token Index: 624

Text #5

Max Range: 7.9789. Min Range: -7.9789

Max Act: 7.7914. Min Act: -0.1700

Data Index: 9209 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 7.9789. Min Range: -7.9789

Max Act: 7.6977. Min Act: -0.1700

Data Index: 1340343 (C4 (Web Text))

Max Activating Token Index: 442

Text #7

Max Range: 7.9789. Min Range: -7.9789

Max Act: 7.7602. Min Act: -0.1700

Data Index: 1110109 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 7.9789. Min Range: -7.9789

Max Act: 7.7289. Min Act: -0.1697

Data Index: 27753 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 7.9789. Min Range: -7.9789

Max Act: 7.6664. Min Act: -0.1700

Data Index: 1073489 (C4 (Web Text))

Max Activating Token Index: 1009

Text #10

Max Range: 7.9789. Min Range: -7.9789

Max Act: 7.6977. Min Act: -0.1700

Data Index: 383056 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 7.9789. Min Range: -7.9789

Max Act: 7.6664. Min Act: -0.1699

Data Index: 833289 (C4 (Web Text))

Max Activating Token Index: 1009

Text #12

Max Range: 7.9789. Min Range: -7.9789

Max Act: 7.6664. Min Act: -0.1700

Data Index: 653409 (C4 (Web Text))

Max Activating Token Index: 288

Text #13

Max Range: 7.9789. Min Range: -7.9789

Max Act: 7.6664. Min Act: -0.1700

Data Index: 356743 (C4 (Web Text))

Max Activating Token Index: 933

Text #14

Max Range: 7.9789. Min Range: -7.9789

Max Act: 7.6977. Min Act: -0.1700

Data Index: 1048050 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 7.9789. Min Range: -7.9789

Max Act: 7.6352. Min Act: -0.1700

Data Index: 448800 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 7.9789. Min Range: -7.9789

Max Act: 7.6352. Min Act: -0.1700

Data Index: 736062 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 7.9789. Min Range: -7.9789

Max Act: 7.5414. Min Act: -0.1700

Data Index: 845023 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 7.9789. Min Range: -7.9789

Max Act: 7.6039. Min Act: -0.1700

Data Index: 236706 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 7.9789. Min Range: -7.9789

Max Act: 7.6664. Min Act: -0.1700

Data Index: 629477 (C4 (Web Text))

Max Activating Token Index: 412