Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1906 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.7963. Min Act: -0.1700

Data Index: 983091 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.7719. Min Act: -0.1700

Data Index: 968663 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.7895. Min Act: -0.1700

Data Index: 509 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.7555. Min Act: -0.1699

Data Index: 660364 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.7338. Min Act: -0.1700

Data Index: 432599 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.7317. Min Act: -0.1700

Data Index: 728301 (C4 (Web Text))

Max Activating Token Index: 256

Text #6

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.7237. Min Act: -0.1699

Data Index: 322938 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.7134. Min Act: -0.1694

Data Index: 1529722 (Python Code)

Max Activating Token Index: 726

Text #8

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.7200. Min Act: -0.1698

Data Index: 42769 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.7012. Min Act: -0.1700

Data Index: 459486 (C4 (Web Text))

Max Activating Token Index: 843

Text #10

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.6944. Min Act: -0.1700

Data Index: 1235057 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.6981. Min Act: -0.1700

Data Index: 1280801 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.7009. Min Act: -0.1700

Data Index: 1304147 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.7016. Min Act: -0.1700

Data Index: 649078 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.6922. Min Act: -0.1700

Data Index: 580990 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.7006. Min Act: -0.1700

Data Index: 1156813 (C4 (Web Text))

Max Activating Token Index: 238

Text #16

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.6835. Min Act: -0.1693

Data Index: 1354446 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.6643. Min Act: -0.1700

Data Index: 310922 (C4 (Web Text))

Max Activating Token Index: 706

Text #18

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.6583. Min Act: -0.1700

Data Index: 412992 (C4 (Web Text))

Max Activating Token Index: 635

Text #19

Max Range: 2.7963. Min Range: -2.7963

Max Act: 2.6618. Min Act: -0.1700

Data Index: 449350 (C4 (Web Text))

Max Activating Token Index: 411