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

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

Neuron 1646 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3450. Min Range: -5.3450

Max Act: 5.3450. Min Act: -0.1700

Data Index: 1383270 (Python Code)

Max Activating Token Index: 234

Text #1

Max Range: 5.3450. Min Range: -5.3450

Max Act: 5.3450. Min Act: -0.1700

Data Index: 1490527 (Python Code)

Max Activating Token Index: 377

Text #2

Max Range: 5.3450. Min Range: -5.3450

Max Act: 5.3138. Min Act: -0.1700

Data Index: 1651986 (Python Code)

Max Activating Token Index: 289

Text #3

Max Range: 5.3450. Min Range: -5.3450

Max Act: 5.3138. Min Act: -0.1700

Data Index: 1378216 (Python Code)

Max Activating Token Index: 865

Text #4

Max Range: 5.3450. Min Range: -5.3450

Max Act: 5.3138. Min Act: -0.1700

Data Index: 1541912 (Python Code)

Max Activating Token Index: 410

Text #5

Max Range: 5.3450. Min Range: -5.3450

Max Act: 5.2825. Min Act: -0.1700

Data Index: 1597052 (Python Code)

Max Activating Token Index: 446

Text #6

Max Range: 5.3450. Min Range: -5.3450

Max Act: 5.2513. Min Act: -0.1700

Data Index: 1515099 (Python Code)

Max Activating Token Index: 648

Text #7

Max Range: 5.3450. Min Range: -5.3450

Max Act: 5.2513. Min Act: -0.1700

Data Index: 1521087 (Python Code)

Max Activating Token Index: 171

Text #8

Max Range: 5.3450. Min Range: -5.3450

Max Act: 5.2200. Min Act: -0.1700

Data Index: 1472318 (Python Code)

Max Activating Token Index: 867

Text #9

Max Range: 5.3450. Min Range: -5.3450

Max Act: 5.2513. Min Act: -0.1700

Data Index: 1598557 (Python Code)

Max Activating Token Index: 458

Text #10

Max Range: 5.3450. Min Range: -5.3450

Max Act: 5.1888. Min Act: -0.1700

Data Index: 1390756 (Python Code)

Max Activating Token Index: 246

Text #11

Max Range: 5.3450. Min Range: -5.3450

Max Act: 5.1888. Min Act: -0.1699

Data Index: 1406761 (Python Code)

Max Activating Token Index: 498

Text #12

Max Range: 5.3450. Min Range: -5.3450

Max Act: 5.1575. Min Act: -0.1700

Data Index: 1600338 (Python Code)

Max Activating Token Index: 406

Text #13

Max Range: 5.3450. Min Range: -5.3450

Max Act: 5.1575. Min Act: -0.1700

Data Index: 1486412 (Python Code)

Max Activating Token Index: 800

Text #14

Max Range: 5.3450. Min Range: -5.3450

Max Act: 5.1575. Min Act: -0.1700

Data Index: 1418961 (Python Code)

Max Activating Token Index: 539

Text #15

Max Range: 5.3450. Min Range: -5.3450

Max Act: 5.1263. Min Act: -0.1700

Data Index: 1374419 (Python Code)

Max Activating Token Index: 689

Text #16

Max Range: 5.3450. Min Range: -5.3450

Max Act: 5.1263. Min Act: -0.1700

Data Index: 1615438 (Python Code)

Max Activating Token Index: 602

Text #17

Max Range: 5.3450. Min Range: -5.3450

Max Act: 5.0950. Min Act: -0.1700

Data Index: 577008 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 5.3450. Min Range: -5.3450

Max Act: 5.0950. Min Act: -0.1699

Data Index: 1575628 (Python Code)

Max Activating Token Index: 739

Text #19

Max Range: 5.3450. Min Range: -5.3450

Max Act: 5.0950. Min Act: -0.1700

Data Index: 1390499 (Python Code)

Max Activating Token Index: 238