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

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

Neuron 148 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9579. Min Range: -5.9579

Max Act: 5.9579. Min Act: -0.1700

Data Index: 1522625 (Python Code)

Max Activating Token Index: 75

Text #1

Max Range: 5.9579. Min Range: -5.9579

Max Act: 5.8329. Min Act: -0.1700

Data Index: 1646712 (Python Code)

Max Activating Token Index: 824

Text #2

Max Range: 5.9579. Min Range: -5.9579

Max Act: 5.8954. Min Act: -0.1700

Data Index: 1555683 (Python Code)

Max Activating Token Index: 840

Text #3

Max Range: 5.9579. Min Range: -5.9579

Max Act: 5.8641. Min Act: -0.1700

Data Index: 1602637 (Python Code)

Max Activating Token Index: 439

Text #4

Max Range: 5.9579. Min Range: -5.9579

Max Act: 5.8954. Min Act: -0.1700

Data Index: 1579488 (Python Code)

Max Activating Token Index: 635

Text #5

Max Range: 5.9579. Min Range: -5.9579

Max Act: 5.8016. Min Act: -0.1700

Data Index: 1609571 (Python Code)

Max Activating Token Index: 466

Text #6

Max Range: 5.9579. Min Range: -5.9579

Max Act: 5.7079. Min Act: -0.1700

Data Index: 1483113 (Python Code)

Max Activating Token Index: 672

Text #7

Max Range: 5.9579. Min Range: -5.9579

Max Act: 5.7391. Min Act: -0.1700

Data Index: 1635123 (Python Code)

Max Activating Token Index: 580

Text #8

Max Range: 5.9579. Min Range: -5.9579

Max Act: 5.9266. Min Act: -0.1700

Data Index: 1382110 (Python Code)

Max Activating Token Index: 770

Text #9

Max Range: 5.9579. Min Range: -5.9579

Max Act: 5.8329. Min Act: -0.1700

Data Index: 1585792 (Python Code)

Max Activating Token Index: 100

Text #10

Max Range: 5.9579. Min Range: -5.9579

Max Act: 5.7704. Min Act: -0.1700

Data Index: 1452745 (Python Code)

Max Activating Token Index: 836

Text #11

Max Range: 5.9579. Min Range: -5.9579

Max Act: 5.8641. Min Act: -0.1700

Data Index: 1491921 (Python Code)

Max Activating Token Index: 797

Text #12

Max Range: 5.9579. Min Range: -5.9579

Max Act: 5.7391. Min Act: -0.1700

Data Index: 1387725 (Python Code)

Max Activating Token Index: 746

Text #13

Max Range: 5.9579. Min Range: -5.9579

Max Act: 5.7391. Min Act: -0.1700

Data Index: 1558898 (Python Code)

Max Activating Token Index: 978

Text #14

Max Range: 5.9579. Min Range: -5.9579

Max Act: 5.7391. Min Act: -0.1700

Data Index: 1367239 (Python Code)

Max Activating Token Index: 531

Text #15

Max Range: 5.9579. Min Range: -5.9579

Max Act: 5.7704. Min Act: -0.1700

Data Index: 1362386 (Python Code)

Max Activating Token Index: 508

Text #16

Max Range: 5.9579. Min Range: -5.9579

Max Act: 5.6766. Min Act: -0.1700

Data Index: 1456209 (Python Code)

Max Activating Token Index: 45

Text #17

Max Range: 5.9579. Min Range: -5.9579

Max Act: 5.6454. Min Act: -0.1700

Data Index: 1457152 (Python Code)

Max Activating Token Index: 373

Text #18

Max Range: 5.9579. Min Range: -5.9579

Max Act: 5.6454. Min Act: -0.1700

Data Index: 1367588 (Python Code)

Max Activating Token Index: 967

Text #19

Max Range: 5.9579. Min Range: -5.9579

Max Act: 5.6454. Min Act: -0.1700

Data Index: 1445616 (Python Code)

Max Activating Token Index: 87