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

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

Neuron 1783 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2477. Min Range: -5.2477

Max Act: 5.2477. Min Act: -0.1700

Data Index: 787743 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 5.2477. Min Range: -5.2477

Max Act: 5.1852. Min Act: -0.1700

Data Index: 795938 (C4 (Web Text))

Max Activating Token Index: 140

Text #2

Max Range: 5.2477. Min Range: -5.2477

Max Act: 5.1227. Min Act: -0.1700

Data Index: 864460 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 5.2477. Min Range: -5.2477

Max Act: 5.1227. Min Act: -0.1700

Data Index: 310932 (C4 (Web Text))

Max Activating Token Index: 837

Text #4

Max Range: 5.2477. Min Range: -5.2477

Max Act: 5.0914. Min Act: -0.1700

Data Index: 679753 (C4 (Web Text))

Max Activating Token Index: 492

Text #5

Max Range: 5.2477. Min Range: -5.2477

Max Act: 5.1227. Min Act: -0.1700

Data Index: 530902 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 5.2477. Min Range: -5.2477

Max Act: 5.0914. Min Act: -0.1700

Data Index: 665097 (C4 (Web Text))

Max Activating Token Index: 585

Text #7

Max Range: 5.2477. Min Range: -5.2477

Max Act: 5.0914. Min Act: -0.1700

Data Index: 930118 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.9977. Min Act: -0.1700

Data Index: 511690 (C4 (Web Text))

Max Activating Token Index: 317

Text #9

Max Range: 5.2477. Min Range: -5.2477

Max Act: 5.0914. Min Act: -0.1700

Data Index: 66248 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 5.2477. Min Range: -5.2477

Max Act: 5.0914. Min Act: -0.1700

Data Index: 1017719 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.9977. Min Act: -0.1700

Data Index: 357531 (C4 (Web Text))

Max Activating Token Index: 959

Text #12

Max Range: 5.2477. Min Range: -5.2477

Max Act: 5.0289. Min Act: -0.1700

Data Index: 165393 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 5.2477. Min Range: -5.2477

Max Act: 5.0289. Min Act: -0.1700

Data Index: 38452 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 5.2477. Min Range: -5.2477

Max Act: 5.0289. Min Act: -0.1700

Data Index: 685196 (C4 (Web Text))

Max Activating Token Index: 899

Text #15

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.9664. Min Act: -0.1700

Data Index: 436041 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.9664. Min Act: -0.1700

Data Index: 922566 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.9664. Min Act: -0.1700

Data Index: 319336 (C4 (Web Text))

Max Activating Token Index: 845

Text #18

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.9977. Min Act: -0.1700

Data Index: 273523 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 5.2477. Min Range: -5.2477

Max Act: 4.9352. Min Act: -0.1700

Data Index: 955286 (C4 (Web Text))

Max Activating Token Index: 885