Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1860 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 4.1368. Min Range: -4.1368

Max Act: 4.1368. Min Act: -0.1700

Data Index: 1387765 (Python Code)

Max Activating Token Index: 884

Text #1

Max Range: 4.1368. Min Range: -4.1368

Max Act: 4.1368. Min Act: -0.1700

Data Index: 1515182 (Python Code)

Max Activating Token Index: 631

Text #2

Max Range: 4.1368. Min Range: -4.1368

Max Act: 4.0743. Min Act: -0.1700

Data Index: 1442734 (Python Code)

Max Activating Token Index: 587

Text #3

Max Range: 4.1368. Min Range: -4.1368

Max Act: 4.1212. Min Act: -0.1700

Data Index: 1574871 (Python Code)

Max Activating Token Index: 788

Text #4

Max Range: 4.1368. Min Range: -4.1368

Max Act: 4.0587. Min Act: -0.1700

Data Index: 1618486 (Python Code)

Max Activating Token Index: 528

Text #5

Max Range: 4.1368. Min Range: -4.1368

Max Act: 4.0431. Min Act: -0.1700

Data Index: 1374474 (Python Code)

Max Activating Token Index: 757

Text #6

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9805. Min Act: -0.1700

Data Index: 1297314 (C4 (Web Text))

Max Activating Token Index: 1005

Text #7

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9493. Min Act: -0.1700

Data Index: 1551198 (Python Code)

Max Activating Token Index: 459

Text #8

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9805. Min Act: -0.1700

Data Index: 112490 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9962. Min Act: -0.1677

Data Index: 1636295 (Python Code)

Max Activating Token Index: 553

Text #10

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9805. Min Act: -0.1700

Data Index: 1452487 (Python Code)

Max Activating Token Index: 548

Text #11

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9805. Min Act: -0.1700

Data Index: 1614449 (Python Code)

Max Activating Token Index: 596

Text #12

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9336. Min Act: -0.1700

Data Index: 1612686 (Python Code)

Max Activating Token Index: 837

Text #13

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9336. Min Act: -0.1700

Data Index: 1382978 (Python Code)

Max Activating Token Index: 411

Text #14

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9336. Min Act: -0.1700

Data Index: 54524 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9336. Min Act: -0.1700

Data Index: 1423700 (Python Code)

Max Activating Token Index: 952

Text #16

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9649. Min Act: -0.1699

Data Index: 1521940 (Python Code)

Max Activating Token Index: 1003

Text #17

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9493. Min Act: -0.1700

Data Index: 1264504 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9336. Min Act: -0.1700

Data Index: 1490020 (Python Code)

Max Activating Token Index: 994

Text #19

Max Range: 4.1368. Min Range: -4.1368

Max Act: 3.9180. Min Act: -0.1700

Data Index: 545182 (C4 (Web Text))

Max Activating Token Index: 774