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

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

Neuron 945 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: 3.8083. Min Range: -3.8083

Max Act: 3.8083. Min Act: -0.1700

Data Index: 1412177 (Python Code)

Max Activating Token Index: 726

Text #1

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.6862. Min Act: -0.1690

Data Index: 1397783 (Python Code)

Max Activating Token Index: 742

Text #2

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.6893. Min Act: -0.1700

Data Index: 1377151 (Python Code)

Max Activating Token Index: 869

Text #3

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.6856. Min Act: -0.1698

Data Index: 1409844 (Python Code)

Max Activating Token Index: 210

Text #4

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.6452. Min Act: -0.1700

Data Index: 1274213 (C4 (Web Text))

Max Activating Token Index: 266

Text #5

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.5989. Min Act: -0.1700

Data Index: 243178 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.5793. Min Act: -0.1659

Data Index: 1612197 (Python Code)

Max Activating Token Index: 794

Text #7

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.5729. Min Act: -0.1700

Data Index: 1518564 (Python Code)

Max Activating Token Index: 218

Text #8

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.5664. Min Act: -0.1700

Data Index: 1568156 (Python Code)

Max Activating Token Index: 225

Text #9

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.5629. Min Act: -0.1700

Data Index: 1544739 (Python Code)

Max Activating Token Index: 337

Text #10

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.5383. Min Act: -0.1700

Data Index: 968727 (C4 (Web Text))

Max Activating Token Index: 711

Text #11

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.5196. Min Act: -0.1699

Data Index: 578782 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.5359. Min Act: -0.1567

Data Index: 1125259 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.5070. Min Act: -0.1700

Data Index: 1612705 (Python Code)

Max Activating Token Index: 989

Text #14

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.5315. Min Act: -0.1699

Data Index: 1371679 (Python Code)

Max Activating Token Index: 959

Text #15

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.5115. Min Act: -0.1696

Data Index: 1521910 (Python Code)

Max Activating Token Index: 290

Text #16

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.5014. Min Act: -0.1607

Data Index: 1433640 (Python Code)

Max Activating Token Index: 210

Text #17

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.4767. Min Act: -0.1700

Data Index: 1580630 (Python Code)

Max Activating Token Index: 393

Text #18

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.4741. Min Act: -0.1700

Data Index: 1426161 (Python Code)

Max Activating Token Index: 484

Text #19

Max Range: 3.8083. Min Range: -3.8083

Max Act: 3.4438. Min Act: -0.1700

Data Index: 1517213 (Python Code)

Max Activating Token Index: 390