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

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

Neuron 592 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3329. Min Range: -7.3329

Max Act: 7.3329. Min Act: -0.1700

Data Index: 1390427 (Python Code)

Max Activating Token Index: 791

Text #1

Max Range: 7.3329. Min Range: -7.3329

Max Act: 7.3016. Min Act: -0.1700

Data Index: 1521115 (Python Code)

Max Activating Token Index: 172

Text #2

Max Range: 7.3329. Min Range: -7.3329

Max Act: 7.1454. Min Act: -0.1700

Data Index: 1624439 (Python Code)

Max Activating Token Index: 461

Text #3

Max Range: 7.3329. Min Range: -7.3329

Max Act: 7.0829. Min Act: -0.1700

Data Index: 1562420 (Python Code)

Max Activating Token Index: 810

Text #4

Max Range: 7.3329. Min Range: -7.3329

Max Act: 6.9579. Min Act: -0.1700

Data Index: 1643275 (Python Code)

Max Activating Token Index: 823

Text #5

Max Range: 7.3329. Min Range: -7.3329

Max Act: 6.9891. Min Act: -0.1700

Data Index: 1630844 (Python Code)

Max Activating Token Index: 301

Text #6

Max Range: 7.3329. Min Range: -7.3329

Max Act: 6.8954. Min Act: -0.1700

Data Index: 1413008 (Python Code)

Max Activating Token Index: 50

Text #7

Max Range: 7.3329. Min Range: -7.3329

Max Act: 6.6766. Min Act: -0.1700

Data Index: 1551969 (Python Code)

Max Activating Token Index: 655

Text #8

Max Range: 7.3329. Min Range: -7.3329

Max Act: 6.7391. Min Act: -0.1700

Data Index: 1411635 (Python Code)

Max Activating Token Index: 782

Text #9

Max Range: 7.3329. Min Range: -7.3329

Max Act: 6.6766. Min Act: -0.1700

Data Index: 1504231 (Python Code)

Max Activating Token Index: 457

Text #10

Max Range: 7.3329. Min Range: -7.3329

Max Act: 6.6766. Min Act: -0.1700

Data Index: 1602316 (Python Code)

Max Activating Token Index: 512

Text #11

Max Range: 7.3329. Min Range: -7.3329

Max Act: 6.6454. Min Act: -0.1700

Data Index: 1597823 (Python Code)

Max Activating Token Index: 252

Text #12

Max Range: 7.3329. Min Range: -7.3329

Max Act: 6.6454. Min Act: -0.1700

Data Index: 1388988 (Python Code)

Max Activating Token Index: 83

Text #13

Max Range: 7.3329. Min Range: -7.3329

Max Act: 6.6454. Min Act: -0.1700

Data Index: 1359890 (Python Code)

Max Activating Token Index: 48

Text #14

Max Range: 7.3329. Min Range: -7.3329

Max Act: 6.6141. Min Act: -0.1700

Data Index: 1635357 (Python Code)

Max Activating Token Index: 681

Text #15

Max Range: 7.3329. Min Range: -7.3329

Max Act: 6.6454. Min Act: -0.1700

Data Index: 1383047 (Python Code)

Max Activating Token Index: 542

Text #16

Max Range: 7.3329. Min Range: -7.3329

Max Act: 6.6766. Min Act: -0.1700

Data Index: 1575151 (Python Code)

Max Activating Token Index: 24

Text #17

Max Range: 7.3329. Min Range: -7.3329

Max Act: 6.6141. Min Act: -0.1700

Data Index: 1524110 (Python Code)

Max Activating Token Index: 432

Text #18

Max Range: 7.3329. Min Range: -7.3329

Max Act: 6.5829. Min Act: -0.1700

Data Index: 1499649 (Python Code)

Max Activating Token Index: 1008

Text #19

Max Range: 7.3329. Min Range: -7.3329

Max Act: 6.6454. Min Act: -0.1700

Data Index: 1406789 (Python Code)

Max Activating Token Index: 21