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

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

Neuron 1365 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: 5.6789. Min Range: -5.6789

Max Act: 5.6789. Min Act: -0.1700

Data Index: 415923 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 5.6789. Min Range: -5.6789

Max Act: 5.4914. Min Act: -0.1700

Data Index: 156362 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 5.6789. Min Range: -5.6789

Max Act: 5.3664. Min Act: -0.1700

Data Index: 741696 (C4 (Web Text))

Max Activating Token Index: 907

Text #3

Max Range: 5.6789. Min Range: -5.6789

Max Act: 5.5226. Min Act: -0.1700

Data Index: 587022 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 5.6789. Min Range: -5.6789

Max Act: 5.4289. Min Act: -0.1700

Data Index: 581120 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 5.6789. Min Range: -5.6789

Max Act: 5.4914. Min Act: -0.1700

Data Index: 1009365 (C4 (Web Text))

Max Activating Token Index: 901

Text #6

Max Range: 5.6789. Min Range: -5.6789

Max Act: 5.3976. Min Act: -0.1700

Data Index: 1209803 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 5.6789. Min Range: -5.6789

Max Act: 5.4289. Min Act: -0.1700

Data Index: 411803 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 5.6789. Min Range: -5.6789

Max Act: 5.3976. Min Act: -0.1700

Data Index: 314008 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 5.6789. Min Range: -5.6789

Max Act: 5.3664. Min Act: -0.1700

Data Index: 742667 (C4 (Web Text))

Max Activating Token Index: 757

Text #10

Max Range: 5.6789. Min Range: -5.6789

Max Act: 5.3976. Min Act: -0.1700

Data Index: 635486 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 5.6789. Min Range: -5.6789

Max Act: 5.3039. Min Act: -0.1700

Data Index: 630755 (C4 (Web Text))

Max Activating Token Index: 266

Text #12

Max Range: 5.6789. Min Range: -5.6789

Max Act: 5.3664. Min Act: -0.1700

Data Index: 936659 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 5.6789. Min Range: -5.6789

Max Act: 5.3664. Min Act: -0.1700

Data Index: 1199174 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 5.6789. Min Range: -5.6789

Max Act: 5.3351. Min Act: -0.1700

Data Index: 448326 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 5.6789. Min Range: -5.6789

Max Act: 5.3351. Min Act: -0.1700

Data Index: 56556 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 5.6789. Min Range: -5.6789

Max Act: 5.3664. Min Act: -0.1700

Data Index: 813869 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 5.6789. Min Range: -5.6789

Max Act: 5.3039. Min Act: -0.1700

Data Index: 609265 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 5.6789. Min Range: -5.6789

Max Act: 5.2414. Min Act: -0.1700

Data Index: 144525 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 5.6789. Min Range: -5.6789

Max Act: 5.2414. Min Act: -0.1700

Data Index: 1300228 (C4 (Web Text))

Max Activating Token Index: 498