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

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

Neuron 1362 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: 3.9724. Min Range: -3.9724

Max Act: 3.9724. Min Act: -0.1700

Data Index: 172937 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 3.9724. Min Range: -3.9724

Max Act: 3.9255. Min Act: -0.1700

Data Index: 223339 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 3.9724. Min Range: -3.9724

Max Act: 3.8317. Min Act: -0.1700

Data Index: 1068731 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 3.9724. Min Range: -3.9724

Max Act: 3.8786. Min Act: -0.1700

Data Index: 678861 (C4 (Web Text))

Max Activating Token Index: 711

Text #4

Max Range: 3.9724. Min Range: -3.9724

Max Act: 3.8474. Min Act: -0.1700

Data Index: 393433 (C4 (Web Text))

Max Activating Token Index: 789

Text #5

Max Range: 3.9724. Min Range: -3.9724

Max Act: 3.7692. Min Act: -0.1700

Data Index: 350449 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 3.9724. Min Range: -3.9724

Max Act: 3.7535. Min Act: -0.1700

Data Index: 1198693 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 3.9724. Min Range: -3.9724

Max Act: 3.7535. Min Act: -0.1700

Data Index: 215472 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 3.9724. Min Range: -3.9724

Max Act: 3.7692. Min Act: -0.1700

Data Index: 748412 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 3.9724. Min Range: -3.9724

Max Act: 3.7692. Min Act: -0.1700

Data Index: 1054227 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 3.9724. Min Range: -3.9724

Max Act: 3.6909. Min Act: -0.1700

Data Index: 702393 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 3.9724. Min Range: -3.9724

Max Act: 3.7222. Min Act: -0.1700

Data Index: 1094684 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 3.9724. Min Range: -3.9724

Max Act: 3.7066. Min Act: -0.1700

Data Index: 1143000 (C4 (Web Text))

Max Activating Token Index: 987

Text #13

Max Range: 3.9724. Min Range: -3.9724

Max Act: 3.7222. Min Act: -0.1700

Data Index: 18363 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 3.9724. Min Range: -3.9724

Max Act: 3.7066. Min Act: -0.1700

Data Index: 1356964 (C4 (Web Text))

Max Activating Token Index: 548

Text #15

Max Range: 3.9724. Min Range: -3.9724

Max Act: 3.6909. Min Act: -0.1700

Data Index: 386688 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 3.9724. Min Range: -3.9724

Max Act: 3.6753. Min Act: -0.1700

Data Index: 1085823 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 3.9724. Min Range: -3.9724

Max Act: 3.6909. Min Act: -0.1700

Data Index: 31587 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 3.9724. Min Range: -3.9724

Max Act: 3.6909. Min Act: -0.1700

Data Index: 933755 (C4 (Web Text))

Max Activating Token Index: 403

Text #19

Max Range: 3.9724. Min Range: -3.9724

Max Act: 3.7222. Min Act: -0.1700

Data Index: 170825 (C4 (Web Text))

Max Activating Token Index: 385