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

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

Neuron 1580 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: 3.6561. Min Range: -3.6561

Max Act: 3.6561. Min Act: -0.1700

Data Index: 1199381 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 3.6561. Min Range: -3.6561

Max Act: 3.6561. Min Act: -0.1700

Data Index: 246861 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 3.6561. Min Range: -3.6561

Max Act: 3.6561. Min Act: -0.1700

Data Index: 106193 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 3.6561. Min Range: -3.6561

Max Act: 3.5935. Min Act: -0.1700

Data Index: 1278340 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 3.6561. Min Range: -3.6561

Max Act: 3.5621. Min Act: -0.1700

Data Index: 356402 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 3.6561. Min Range: -3.6561

Max Act: 3.6248. Min Act: -0.1700

Data Index: 722637 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 3.6561. Min Range: -3.6561

Max Act: 3.5621. Min Act: -0.1700

Data Index: 258858 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 3.6561. Min Range: -3.6561

Max Act: 3.5935. Min Act: -0.1700

Data Index: 423543 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 3.6561. Min Range: -3.6561

Max Act: 3.5621. Min Act: -0.1700

Data Index: 944843 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 3.6561. Min Range: -3.6561

Max Act: 3.5308. Min Act: -0.1700

Data Index: 27643 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 3.6561. Min Range: -3.6561

Max Act: 3.5151. Min Act: -0.1700

Data Index: 424338 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 3.6561. Min Range: -3.6561

Max Act: 3.5308. Min Act: -0.1700

Data Index: 1045589 (C4 (Web Text))

Max Activating Token Index: 968

Text #12

Max Range: 3.6561. Min Range: -3.6561

Max Act: 3.5308. Min Act: -0.1700

Data Index: 713622 (C4 (Web Text))

Max Activating Token Index: 419

Text #13

Max Range: 3.6561. Min Range: -3.6561

Max Act: 3.5151. Min Act: -0.1700

Data Index: 1323850 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 3.6561. Min Range: -3.6561

Max Act: 3.5151. Min Act: -0.1700

Data Index: 320113 (C4 (Web Text))

Max Activating Token Index: 124

Text #15

Max Range: 3.6561. Min Range: -3.6561

Max Act: 3.5465. Min Act: -0.1700

Data Index: 1300399 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 3.6561. Min Range: -3.6561

Max Act: 3.5465. Min Act: -0.1700

Data Index: 595538 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 3.6561. Min Range: -3.6561

Max Act: 3.5465. Min Act: -0.1700

Data Index: 1053097 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 3.6561. Min Range: -3.6561

Max Act: 3.5308. Min Act: -0.1700

Data Index: 812289 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 3.6561. Min Range: -3.6561

Max Act: 3.4838. Min Act: -0.1700

Data Index: 131054 (C4 (Web Text))

Max Activating Token Index: 84