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

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

Neuron 1585 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: 7.7537. Min Range: -7.7537

Max Act: 7.7537. Min Act: -0.1700

Data Index: 1619638 (Python Code)

Max Activating Token Index: 608

Text #1

Max Range: 7.7537. Min Range: -7.7537

Max Act: 7.6912. Min Act: -0.1700

Data Index: 1402301 (Python Code)

Max Activating Token Index: 971

Text #2

Max Range: 7.7537. Min Range: -7.7537

Max Act: 7.7537. Min Act: -0.1700

Data Index: 1627359 (Python Code)

Max Activating Token Index: 1004

Text #3

Max Range: 7.7537. Min Range: -7.7537

Max Act: 7.6912. Min Act: -0.1700

Data Index: 1624895 (Python Code)

Max Activating Token Index: 975

Text #4

Max Range: 7.7537. Min Range: -7.7537

Max Act: 7.6912. Min Act: -0.1700

Data Index: 1584668 (Python Code)

Max Activating Token Index: 770

Text #5

Max Range: 7.7537. Min Range: -7.7537

Max Act: 7.6287. Min Act: -0.1700

Data Index: 1399779 (Python Code)

Max Activating Token Index: 787

Text #6

Max Range: 7.7537. Min Range: -7.7537

Max Act: 7.6912. Min Act: -0.1700

Data Index: 1593460 (Python Code)

Max Activating Token Index: 1008

Text #7

Max Range: 7.7537. Min Range: -7.7537

Max Act: 7.6287. Min Act: -0.1700

Data Index: 1621366 (Python Code)

Max Activating Token Index: 885

Text #8

Max Range: 7.7537. Min Range: -7.7537

Max Act: 7.5662. Min Act: -0.1700

Data Index: 1377627 (Python Code)

Max Activating Token Index: 610

Text #9

Max Range: 7.7537. Min Range: -7.7537

Max Act: 7.6287. Min Act: -0.1700

Data Index: 1522527 (Python Code)

Max Activating Token Index: 946

Text #10

Max Range: 7.7537. Min Range: -7.7537

Max Act: 7.6287. Min Act: -0.1700

Data Index: 1528599 (Python Code)

Max Activating Token Index: 981

Text #11

Max Range: 7.7537. Min Range: -7.7537

Max Act: 7.5662. Min Act: -0.1700

Data Index: 1447826 (Python Code)

Max Activating Token Index: 812

Text #12

Max Range: 7.7537. Min Range: -7.7537

Max Act: 7.6287. Min Act: -0.1700

Data Index: 1563312 (Python Code)

Max Activating Token Index: 968

Text #13

Max Range: 7.7537. Min Range: -7.7537

Max Act: 7.6287. Min Act: -0.1700

Data Index: 1479712 (Python Code)

Max Activating Token Index: 1000

Text #14

Max Range: 7.7537. Min Range: -7.7537

Max Act: 7.6287. Min Act: -0.1700

Data Index: 1577541 (Python Code)

Max Activating Token Index: 919

Text #15

Max Range: 7.7537. Min Range: -7.7537

Max Act: 7.6287. Min Act: -0.1700

Data Index: 1580884 (Python Code)

Max Activating Token Index: 945

Text #16

Max Range: 7.7537. Min Range: -7.7537

Max Act: 7.5662. Min Act: -0.1700

Data Index: 1423656 (Python Code)

Max Activating Token Index: 1021

Text #17

Max Range: 7.7537. Min Range: -7.7537

Max Act: 7.5662. Min Act: -0.1700

Data Index: 1557245 (Python Code)

Max Activating Token Index: 893

Text #18

Max Range: 7.7537. Min Range: -7.7537

Max Act: 7.5662. Min Act: -0.1700

Data Index: 1370480 (Python Code)

Max Activating Token Index: 976

Text #19

Max Range: 7.7537. Min Range: -7.7537

Max Act: 7.5662. Min Act: -0.1700

Data Index: 1490183 (Python Code)

Max Activating Token Index: 791