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

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

Neuron 613 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7812. Min Range: -5.7812

Max Act: 5.7812. Min Act: -0.1700

Data Index: 1095624 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 5.7812. Min Range: -5.7812

Max Act: 5.7187. Min Act: -0.1700

Data Index: 811966 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 5.7812. Min Range: -5.7812

Max Act: 5.7499. Min Act: -0.1700

Data Index: 1141475 (C4 (Web Text))

Max Activating Token Index: 915

Text #3

Max Range: 5.7812. Min Range: -5.7812

Max Act: 5.7499. Min Act: -0.1700

Data Index: 492293 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 5.7812. Min Range: -5.7812

Max Act: 5.7187. Min Act: -0.1700

Data Index: 169247 (C4 (Web Text))

Max Activating Token Index: 982

Text #5

Max Range: 5.7812. Min Range: -5.7812

Max Act: 5.6562. Min Act: -0.1700

Data Index: 335687 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 5.7812. Min Range: -5.7812

Max Act: 5.7187. Min Act: -0.1700

Data Index: 185984 (C4 (Web Text))

Max Activating Token Index: 1010

Text #7

Max Range: 5.7812. Min Range: -5.7812

Max Act: 5.6562. Min Act: -0.1700

Data Index: 14193 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 5.7812. Min Range: -5.7812

Max Act: 5.6874. Min Act: -0.1700

Data Index: 1017652 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 5.7812. Min Range: -5.7812

Max Act: 5.6562. Min Act: -0.1700

Data Index: 321416 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 5.7812. Min Range: -5.7812

Max Act: 5.6874. Min Act: -0.1700

Data Index: 1264647 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 5.7812. Min Range: -5.7812

Max Act: 5.6562. Min Act: -0.1700

Data Index: 134137 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 5.7812. Min Range: -5.7812

Max Act: 5.6874. Min Act: -0.1700

Data Index: 466387 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 5.7812. Min Range: -5.7812

Max Act: 5.6249. Min Act: -0.1700

Data Index: 846707 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 5.7812. Min Range: -5.7812

Max Act: 5.6562. Min Act: -0.1700

Data Index: 760100 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 5.7812. Min Range: -5.7812

Max Act: 5.6249. Min Act: -0.1700

Data Index: 581349 (C4 (Web Text))

Max Activating Token Index: 957

Text #16

Max Range: 5.7812. Min Range: -5.7812

Max Act: 5.6562. Min Act: -0.1700

Data Index: 730079 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 5.7812. Min Range: -5.7812

Max Act: 5.6249. Min Act: -0.1700

Data Index: 661683 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 5.7812. Min Range: -5.7812

Max Act: 5.6562. Min Act: -0.1700

Data Index: 372569 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 5.7812. Min Range: -5.7812

Max Act: 5.5937. Min Act: -0.1700

Data Index: 790526 (C4 (Web Text))

Max Activating Token Index: 186