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

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

Neuron 241 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.7375. Min Act: -0.1700

Data Index: 554910 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.7062. Min Act: -0.1700

Data Index: 332350 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.6749. Min Act: -0.1700

Data Index: 1097790 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.6436. Min Act: -0.1700

Data Index: 1234860 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.6436. Min Act: -0.1700

Data Index: 1230221 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.5810. Min Act: -0.1700

Data Index: 171030 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.5810. Min Act: -0.1700

Data Index: 1226601 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.5497. Min Act: -0.1700

Data Index: 1184138 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.4870. Min Act: -0.1700

Data Index: 460929 (C4 (Web Text))

Max Activating Token Index: 284

Text #9

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.4870. Min Act: -0.1700

Data Index: 1157083 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.4870. Min Act: -0.1700

Data Index: 747508 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.4870. Min Act: -0.1700

Data Index: 951354 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.4713. Min Act: -0.1700

Data Index: 831545 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.4870. Min Act: -0.1700

Data Index: 539818 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.4557. Min Act: -0.1700

Data Index: 1348029 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.4400. Min Act: -0.1700

Data Index: 218691 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.3929. Min Act: -0.1700

Data Index: 961841 (C4 (Web Text))

Max Activating Token Index: 444

Text #17

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.3615. Min Act: -0.1700

Data Index: 745575 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.4086. Min Act: -0.1700

Data Index: 518564 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 3.7375. Min Range: -3.7375

Max Act: 3.4243. Min Act: -0.1700

Data Index: 204870 (C4 (Web Text))

Max Activating Token Index: 68