Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2038 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 7.5240. Min Range: -7.5240

Max Act: 7.5240. Min Act: -0.1695

Data Index: 1263036 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 7.5240. Min Range: -7.5240

Max Act: 7.4615. Min Act: -0.1700

Data Index: 806408 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 7.5240. Min Range: -7.5240

Max Act: 6.9927. Min Act: -0.1700

Data Index: 1520583 (Python Code)

Max Activating Token Index: 93

Text #3

Max Range: 7.5240. Min Range: -7.5240

Max Act: 6.8990. Min Act: -0.1700

Data Index: 1497321 (Python Code)

Max Activating Token Index: 109

Text #4

Max Range: 7.5240. Min Range: -7.5240

Max Act: 6.7115. Min Act: -0.1700

Data Index: 1606812 (Python Code)

Max Activating Token Index: 139

Text #5

Max Range: 7.5240. Min Range: -7.5240

Max Act: 6.5552. Min Act: -0.1697

Data Index: 611675 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 7.5240. Min Range: -7.5240

Max Act: 6.4927. Min Act: -0.1700

Data Index: 1548149 (Python Code)

Max Activating Token Index: 531

Text #7

Max Range: 7.5240. Min Range: -7.5240

Max Act: 6.3990. Min Act: -0.1700

Data Index: 1404851 (Python Code)

Max Activating Token Index: 189

Text #8

Max Range: 7.5240. Min Range: -7.5240

Max Act: 6.2427. Min Act: -0.1700

Data Index: 1623922 (Python Code)

Max Activating Token Index: 71

Text #9

Max Range: 7.5240. Min Range: -7.5240

Max Act: 6.2740. Min Act: -0.1700

Data Index: 1609647 (Python Code)

Max Activating Token Index: 670

Text #10

Max Range: 7.5240. Min Range: -7.5240

Max Act: 6.2427. Min Act: -0.1700

Data Index: 1436275 (Python Code)

Max Activating Token Index: 704

Text #11

Max Range: 7.5240. Min Range: -7.5240

Max Act: 6.1490. Min Act: -0.1700

Data Index: 1507974 (Python Code)

Max Activating Token Index: 375

Text #12

Max Range: 7.5240. Min Range: -7.5240

Max Act: 6.1490. Min Act: -0.1700

Data Index: 1416613 (Python Code)

Max Activating Token Index: 347

Text #13

Max Range: 7.5240. Min Range: -7.5240

Max Act: 6.1177. Min Act: -0.1700

Data Index: 1629689 (Python Code)

Max Activating Token Index: 516

Text #14

Max Range: 7.5240. Min Range: -7.5240

Max Act: 6.0865. Min Act: -0.1700

Data Index: 990550 (C4 (Web Text))

Max Activating Token Index: 892

Text #15

Max Range: 7.5240. Min Range: -7.5240

Max Act: 6.0552. Min Act: -0.1700

Data Index: 1518118 (Python Code)

Max Activating Token Index: 551

Text #16

Max Range: 7.5240. Min Range: -7.5240

Max Act: 6.0240. Min Act: -0.1700

Data Index: 1592952 (Python Code)

Max Activating Token Index: 811

Text #17

Max Range: 7.5240. Min Range: -7.5240

Max Act: 5.9927. Min Act: -0.1700

Data Index: 1484540 (Python Code)

Max Activating Token Index: 916

Text #18

Max Range: 7.5240. Min Range: -7.5240

Max Act: 5.9615. Min Act: -0.1700

Data Index: 427553 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 7.5240. Min Range: -7.5240

Max Act: 5.9302. Min Act: -0.1700

Data Index: 45430 (C4 (Web Text))

Max Activating Token Index: 850