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

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

Neuron 772 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9358. Min Range: -3.9358

Max Act: 3.9358. Min Act: -0.1700

Data Index: 1434454 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 3.9358. Min Range: -3.9358

Max Act: 3.8107. Min Act: -0.1700

Data Index: 1454669 (Python Code)

Max Activating Token Index: 888

Text #2

Max Range: 3.9358. Min Range: -3.9358

Max Act: 3.8420. Min Act: -0.1700

Data Index: 1416136 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 3.9358. Min Range: -3.9358

Max Act: 3.8107. Min Act: -0.1700

Data Index: 1605993 (Python Code)

Max Activating Token Index: 699

Text #4

Max Range: 3.9358. Min Range: -3.9358

Max Act: 3.8420. Min Act: -0.1700

Data Index: 1462964 (Python Code)

Max Activating Token Index: 988

Text #5

Max Range: 3.9358. Min Range: -3.9358

Max Act: 3.8733. Min Act: -0.1700

Data Index: 1539244 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 3.9358. Min Range: -3.9358

Max Act: 3.8420. Min Act: -0.1700

Data Index: 1537887 (Python Code)

Max Activating Token Index: 40

Text #7

Max Range: 3.9358. Min Range: -3.9358

Max Act: 3.8420. Min Act: -0.1700

Data Index: 1433784 (Python Code)

Max Activating Token Index: 818

Text #8

Max Range: 3.9358. Min Range: -3.9358

Max Act: 3.8107. Min Act: -0.1700

Data Index: 1408868 (Python Code)

Max Activating Token Index: 530

Text #9

Max Range: 3.9358. Min Range: -3.9358

Max Act: 3.7481. Min Act: -0.1700

Data Index: 1449490 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 3.9358. Min Range: -3.9358

Max Act: 3.7168. Min Act: -0.1700

Data Index: 1494723 (Python Code)

Max Activating Token Index: 696

Text #11

Max Range: 3.9358. Min Range: -3.9358

Max Act: 3.7794. Min Act: -0.1700

Data Index: 1553622 (Python Code)

Max Activating Token Index: 892

Text #12

Max Range: 3.9358. Min Range: -3.9358

Max Act: 3.7794. Min Act: -0.1700

Data Index: 1548084 (Python Code)

Max Activating Token Index: 466

Text #13

Max Range: 3.9358. Min Range: -3.9358

Max Act: 3.7794. Min Act: -0.1700

Data Index: 1496038 (Python Code)

Max Activating Token Index: 737

Text #14

Max Range: 3.9358. Min Range: -3.9358

Max Act: 3.7794. Min Act: -0.1700

Data Index: 1631493 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 3.9358. Min Range: -3.9358

Max Act: 3.6855. Min Act: -0.1700

Data Index: 1606693 (Python Code)

Max Activating Token Index: 375

Text #16

Max Range: 3.9358. Min Range: -3.9358

Max Act: 3.7794. Min Act: -0.1700

Data Index: 1544264 (Python Code)

Max Activating Token Index: 973

Text #17

Max Range: 3.9358. Min Range: -3.9358

Max Act: 3.7481. Min Act: -0.1700

Data Index: 1482962 (Python Code)

Max Activating Token Index: 835

Text #18

Max Range: 3.9358. Min Range: -3.9358

Max Act: 3.7481. Min Act: -0.1700

Data Index: 1529304 (Python Code)

Max Activating Token Index: 693

Text #19

Max Range: 3.9358. Min Range: -3.9358

Max Act: 3.7794. Min Act: -0.1700

Data Index: 1583535 (Python Code)

Max Activating Token Index: 1023