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

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

Neuron 1348 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: 5.8136. Min Range: -5.8136

Max Act: 5.8136. Min Act: -0.1700

Data Index: 1516598 (Python Code)

Max Activating Token Index: 37

Text #1

Max Range: 5.8136. Min Range: -5.8136

Max Act: 5.8136. Min Act: -0.1700

Data Index: 1550296 (Python Code)

Max Activating Token Index: 238

Text #2

Max Range: 5.8136. Min Range: -5.8136

Max Act: 5.7511. Min Act: -0.1700

Data Index: 1634884 (Python Code)

Max Activating Token Index: 521

Text #3

Max Range: 5.8136. Min Range: -5.8136

Max Act: 5.7823. Min Act: -0.1700

Data Index: 1414899 (Python Code)

Max Activating Token Index: 538

Text #4

Max Range: 5.8136. Min Range: -5.8136

Max Act: 5.7823. Min Act: -0.1700

Data Index: 1391340 (Python Code)

Max Activating Token Index: 374

Text #5

Max Range: 5.8136. Min Range: -5.8136

Max Act: 5.7823. Min Act: -0.1700

Data Index: 1472229 (Python Code)

Max Activating Token Index: 403

Text #6

Max Range: 5.8136. Min Range: -5.8136

Max Act: 5.7198. Min Act: -0.1700

Data Index: 1409249 (Python Code)

Max Activating Token Index: 970

Text #7

Max Range: 5.8136. Min Range: -5.8136

Max Act: 5.7511. Min Act: -0.1700

Data Index: 1530332 (Python Code)

Max Activating Token Index: 40

Text #8

Max Range: 5.8136. Min Range: -5.8136

Max Act: 5.6573. Min Act: -0.1700

Data Index: 1624593 (Python Code)

Max Activating Token Index: 55

Text #9

Max Range: 5.8136. Min Range: -5.8136

Max Act: 5.7511. Min Act: -0.1700

Data Index: 1622367 (Python Code)

Max Activating Token Index: 593

Text #10

Max Range: 5.8136. Min Range: -5.8136

Max Act: 5.6573. Min Act: -0.1700

Data Index: 1431371 (Python Code)

Max Activating Token Index: 52

Text #11

Max Range: 5.8136. Min Range: -5.8136

Max Act: 5.7198. Min Act: -0.1700

Data Index: 1479862 (Python Code)

Max Activating Token Index: 219

Text #12

Max Range: 5.8136. Min Range: -5.8136

Max Act: 5.6573. Min Act: -0.1700

Data Index: 1400255 (Python Code)

Max Activating Token Index: 109

Text #13

Max Range: 5.8136. Min Range: -5.8136

Max Act: 5.6573. Min Act: -0.1700

Data Index: 1491508 (Python Code)

Max Activating Token Index: 624

Text #14

Max Range: 5.8136. Min Range: -5.8136

Max Act: 5.6573. Min Act: -0.1700

Data Index: 1368721 (Python Code)

Max Activating Token Index: 440

Text #15

Max Range: 5.8136. Min Range: -5.8136

Max Act: 5.5948. Min Act: -0.1700

Data Index: 1492982 (Python Code)

Max Activating Token Index: 999

Text #16

Max Range: 5.8136. Min Range: -5.8136

Max Act: 5.6573. Min Act: -0.1700

Data Index: 1376592 (Python Code)

Max Activating Token Index: 460

Text #17

Max Range: 5.8136. Min Range: -5.8136

Max Act: 5.6886. Min Act: -0.1700

Data Index: 1549858 (Python Code)

Max Activating Token Index: 375

Text #18

Max Range: 5.8136. Min Range: -5.8136

Max Act: 5.6573. Min Act: -0.1700

Data Index: 1474553 (Python Code)

Max Activating Token Index: 25

Text #19

Max Range: 5.8136. Min Range: -5.8136

Max Act: 5.6261. Min Act: -0.1700

Data Index: 1449843 (Python Code)

Max Activating Token Index: 84