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

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

Neuron 1952 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: 5.6511. Min Range: -5.6511

Max Act: 5.6511. Min Act: -0.1700

Data Index: 1561732 (Python Code)

Max Activating Token Index: 820

Text #1

Max Range: 5.6511. Min Range: -5.6511

Max Act: 5.5417. Min Act: -0.1700

Data Index: 1609619 (Python Code)

Max Activating Token Index: 800

Text #2

Max Range: 5.6511. Min Range: -5.6511

Max Act: 5.5417. Min Act: -0.1700

Data Index: 1416933 (Python Code)

Max Activating Token Index: 858

Text #3

Max Range: 5.6511. Min Range: -5.6511

Max Act: 5.4948. Min Act: -0.1700

Data Index: 1626622 (Python Code)

Max Activating Token Index: 957

Text #4

Max Range: 5.6511. Min Range: -5.6511

Max Act: 5.4792. Min Act: -0.1700

Data Index: 1412954 (Python Code)

Max Activating Token Index: 742

Text #5

Max Range: 5.6511. Min Range: -5.6511

Max Act: 5.4948. Min Act: -0.1700

Data Index: 1597572 (Python Code)

Max Activating Token Index: 994

Text #6

Max Range: 5.6511. Min Range: -5.6511

Max Act: 5.4948. Min Act: -0.1700

Data Index: 1437755 (Python Code)

Max Activating Token Index: 405

Text #7

Max Range: 5.6511. Min Range: -5.6511

Max Act: 5.4167. Min Act: -0.1700

Data Index: 1613521 (Python Code)

Max Activating Token Index: 629

Text #8

Max Range: 5.6511. Min Range: -5.6511

Max Act: 5.3542. Min Act: -0.1700

Data Index: 1639914 (Python Code)

Max Activating Token Index: 734

Text #9

Max Range: 5.6511. Min Range: -5.6511

Max Act: 5.3855. Min Act: -0.1700

Data Index: 1528244 (Python Code)

Max Activating Token Index: 316

Text #10

Max Range: 5.6511. Min Range: -5.6511

Max Act: 5.4323. Min Act: -0.1700

Data Index: 1534744 (Python Code)

Max Activating Token Index: 594

Text #11

Max Range: 5.6511. Min Range: -5.6511

Max Act: 5.4323. Min Act: -0.1700

Data Index: 1500691 (Python Code)

Max Activating Token Index: 722

Text #12

Max Range: 5.6511. Min Range: -5.6511

Max Act: 5.3855. Min Act: -0.1700

Data Index: 1651388 (Python Code)

Max Activating Token Index: 780

Text #13

Max Range: 5.6511. Min Range: -5.6511

Max Act: 5.3542. Min Act: -0.1700

Data Index: 1538929 (Python Code)

Max Activating Token Index: 795

Text #14

Max Range: 5.6511. Min Range: -5.6511

Max Act: 5.3230. Min Act: -0.1700

Data Index: 1616134 (Python Code)

Max Activating Token Index: 744

Text #15

Max Range: 5.6511. Min Range: -5.6511

Max Act: 5.3230. Min Act: -0.1700

Data Index: 1417204 (Python Code)

Max Activating Token Index: 768

Text #16

Max Range: 5.6511. Min Range: -5.6511

Max Act: 5.3073. Min Act: -0.1700

Data Index: 1478514 (Python Code)

Max Activating Token Index: 323

Text #17

Max Range: 5.6511. Min Range: -5.6511

Max Act: 5.3386. Min Act: -0.1700

Data Index: 1439803 (Python Code)

Max Activating Token Index: 925

Text #18

Max Range: 5.6511. Min Range: -5.6511

Max Act: 5.2448. Min Act: -0.1700

Data Index: 1413276 (Python Code)

Max Activating Token Index: 715

Text #19

Max Range: 5.6511. Min Range: -5.6511

Max Act: 5.2448. Min Act: -0.1700

Data Index: 1450765 (Python Code)

Max Activating Token Index: 691