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

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

Neuron 505 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9836. Min Range: -3.9836

Max Act: 3.9836. Min Act: -0.1700

Data Index: 1552429 (Python Code)

Max Activating Token Index: 382

Text #1

Max Range: 3.9836. Min Range: -3.9836

Max Act: 3.7334. Min Act: -0.1700

Data Index: 1472816 (Python Code)

Max Activating Token Index: 191

Text #2

Max Range: 3.9836. Min Range: -3.9836

Max Act: 3.7334. Min Act: -0.1700

Data Index: 1522296 (Python Code)

Max Activating Token Index: 799

Text #3

Max Range: 3.9836. Min Range: -3.9836

Max Act: 3.7021. Min Act: -0.1700

Data Index: 1434768 (Python Code)

Max Activating Token Index: 494

Text #4

Max Range: 3.9836. Min Range: -3.9836

Max Act: 3.7334. Min Act: -0.1700

Data Index: 1393958 (Python Code)

Max Activating Token Index: 840

Text #5

Max Range: 3.9836. Min Range: -3.9836

Max Act: 3.6708. Min Act: -0.1700

Data Index: 1543739 (Python Code)

Max Activating Token Index: 14

Text #6

Max Range: 3.9836. Min Range: -3.9836

Max Act: 3.6708. Min Act: -0.1700

Data Index: 1608670 (Python Code)

Max Activating Token Index: 585

Text #7

Max Range: 3.9836. Min Range: -3.9836

Max Act: 3.7021. Min Act: -0.1700

Data Index: 1606693 (Python Code)

Max Activating Token Index: 785

Text #8

Max Range: 3.9836. Min Range: -3.9836

Max Act: 3.7021. Min Act: -0.1700

Data Index: 1567877 (Python Code)

Max Activating Token Index: 808

Text #9

Max Range: 3.9836. Min Range: -3.9836

Max Act: 3.7021. Min Act: -0.1700

Data Index: 1409293 (Python Code)

Max Activating Token Index: 456

Text #10

Max Range: 3.9836. Min Range: -3.9836

Max Act: 3.7021. Min Act: -0.1700

Data Index: 1411164 (Python Code)

Max Activating Token Index: 139

Text #11

Max Range: 3.9836. Min Range: -3.9836

Max Act: 3.7021. Min Act: -0.1700

Data Index: 1466480 (Python Code)

Max Activating Token Index: 14

Text #12

Max Range: 3.9836. Min Range: -3.9836

Max Act: 3.7021. Min Act: -0.1700

Data Index: 1360081 (Python Code)

Max Activating Token Index: 355

Text #13

Max Range: 3.9836. Min Range: -3.9836

Max Act: 3.7021. Min Act: -0.1700

Data Index: 1493693 (Python Code)

Max Activating Token Index: 908

Text #14

Max Range: 3.9836. Min Range: -3.9836

Max Act: 3.7334. Min Act: -0.1700

Data Index: 1480381 (Python Code)

Max Activating Token Index: 285

Text #15

Max Range: 3.9836. Min Range: -3.9836

Max Act: 3.6708. Min Act: -0.1700

Data Index: 1544264 (Python Code)

Max Activating Token Index: 536

Text #16

Max Range: 3.9836. Min Range: -3.9836

Max Act: 3.6708. Min Act: -0.1700

Data Index: 1620653 (Python Code)

Max Activating Token Index: 547

Text #17

Max Range: 3.9836. Min Range: -3.9836

Max Act: 3.6708. Min Act: -0.1700

Data Index: 1496471 (Python Code)

Max Activating Token Index: 319

Text #18

Max Range: 3.9836. Min Range: -3.9836

Max Act: 3.7021. Min Act: -0.1700

Data Index: 1470995 (Python Code)

Max Activating Token Index: 632

Text #19

Max Range: 3.9836. Min Range: -3.9836

Max Act: 3.7021. Min Act: -0.1700

Data Index: 1362759 (Python Code)

Max Activating Token Index: 646