Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1889 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.6873. Min Act: -0.1700

Data Index: 1654468 (Python Code)

Max Activating Token Index: 616

Text #1

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.6717. Min Act: -0.1700

Data Index: 1395743 (Python Code)

Max Activating Token Index: 839

Text #2

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.6873. Min Act: -0.1700

Data Index: 1654373 (Python Code)

Max Activating Token Index: 371

Text #3

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.6717. Min Act: -0.1700

Data Index: 1367284 (Python Code)

Max Activating Token Index: 555

Text #4

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.6560. Min Act: -0.1700

Data Index: 1576497 (Python Code)

Max Activating Token Index: 381

Text #5

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.6560. Min Act: -0.1700

Data Index: 1363241 (Python Code)

Max Activating Token Index: 180

Text #6

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.6091. Min Act: -0.1700

Data Index: 1095880 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.6560. Min Act: -0.1700

Data Index: 1419250 (Python Code)

Max Activating Token Index: 609

Text #8

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.6247. Min Act: -0.1700

Data Index: 1532992 (Python Code)

Max Activating Token Index: 881

Text #9

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.6091. Min Act: -0.1700

Data Index: 1414443 (Python Code)

Max Activating Token Index: 666

Text #10

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.6091. Min Act: -0.1700

Data Index: 2402 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.6247. Min Act: -0.1700

Data Index: 1389162 (Python Code)

Max Activating Token Index: 1022

Text #12

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.5777. Min Act: -0.1700

Data Index: 1422708 (Python Code)

Max Activating Token Index: 770

Text #13

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.5621. Min Act: -0.1700

Data Index: 1610660 (Python Code)

Max Activating Token Index: 731

Text #14

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.5934. Min Act: -0.1700

Data Index: 1332089 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.5621. Min Act: -0.1700

Data Index: 1583975 (Python Code)

Max Activating Token Index: 384

Text #16

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.5621. Min Act: -0.1700

Data Index: 1541590 (Python Code)

Max Activating Token Index: 675

Text #17

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.5308. Min Act: -0.1700

Data Index: 1538396 (Python Code)

Max Activating Token Index: 644

Text #18

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.5621. Min Act: -0.1700

Data Index: 1641521 (Python Code)

Max Activating Token Index: 976

Text #19

Max Range: 3.6873. Min Range: -3.6873

Max Act: 3.5777. Min Act: -0.1700

Data Index: 1529091 (Python Code)

Max Activating Token Index: 636