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

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

Neuron 1949 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: 3.5454. Min Range: -3.5454

Max Act: 3.5454. Min Act: -0.1700

Data Index: 1448815 (Python Code)

Max Activating Token Index: 290

Text #1

Max Range: 3.5454. Min Range: -3.5454

Max Act: 3.5141. Min Act: -0.1700

Data Index: 1573969 (Python Code)

Max Activating Token Index: 578

Text #2

Max Range: 3.5454. Min Range: -3.5454

Max Act: 3.4985. Min Act: -0.1700

Data Index: 1403091 (Python Code)

Max Activating Token Index: 610

Text #3

Max Range: 3.5454. Min Range: -3.5454

Max Act: 3.5141. Min Act: -0.1700

Data Index: 1653795 (Python Code)

Max Activating Token Index: 705

Text #4

Max Range: 3.5454. Min Range: -3.5454

Max Act: 3.4985. Min Act: -0.1700

Data Index: 1551711 (Python Code)

Max Activating Token Index: 530

Text #5

Max Range: 3.5454. Min Range: -3.5454

Max Act: 3.4828. Min Act: -0.1700

Data Index: 1420029 (Python Code)

Max Activating Token Index: 220

Text #6

Max Range: 3.5454. Min Range: -3.5454

Max Act: 3.4671. Min Act: -0.1700

Data Index: 1527136 (Python Code)

Max Activating Token Index: 394

Text #7

Max Range: 3.5454. Min Range: -3.5454

Max Act: 3.4828. Min Act: -0.1700

Data Index: 1447854 (Python Code)

Max Activating Token Index: 812

Text #8

Max Range: 3.5454. Min Range: -3.5454

Max Act: 3.4671. Min Act: -0.1700

Data Index: 1440313 (Python Code)

Max Activating Token Index: 61

Text #9

Max Range: 3.5454. Min Range: -3.5454

Max Act: 3.4671. Min Act: -0.1700

Data Index: 1508224 (Python Code)

Max Activating Token Index: 27

Text #10

Max Range: 3.5454. Min Range: -3.5454

Max Act: 3.4671. Min Act: -0.1700

Data Index: 1469756 (Python Code)

Max Activating Token Index: 728

Text #11

Max Range: 3.5454. Min Range: -3.5454

Max Act: 3.4514. Min Act: -0.1700

Data Index: 1497213 (Python Code)

Max Activating Token Index: 83

Text #12

Max Range: 3.5454. Min Range: -3.5454

Max Act: 3.4514. Min Act: -0.1700

Data Index: 1424901 (Python Code)

Max Activating Token Index: 26

Text #13

Max Range: 3.5454. Min Range: -3.5454

Max Act: 3.4358. Min Act: -0.1700

Data Index: 1570255 (Python Code)

Max Activating Token Index: 213

Text #14

Max Range: 3.5454. Min Range: -3.5454

Max Act: 3.4514. Min Act: -0.1700

Data Index: 1655277 (Python Code)

Max Activating Token Index: 181

Text #15

Max Range: 3.5454. Min Range: -3.5454

Max Act: 3.4514. Min Act: -0.1700

Data Index: 1576824 (Python Code)

Max Activating Token Index: 227

Text #16

Max Range: 3.5454. Min Range: -3.5454

Max Act: 3.4514. Min Act: -0.1700

Data Index: 1373878 (Python Code)

Max Activating Token Index: 562

Text #17

Max Range: 3.5454. Min Range: -3.5454

Max Act: 3.4514. Min Act: -0.1700

Data Index: 1544890 (Python Code)

Max Activating Token Index: 1016

Text #18

Max Range: 3.5454. Min Range: -3.5454

Max Act: 3.4358. Min Act: -0.1700

Data Index: 1446987 (Python Code)

Max Activating Token Index: 144

Text #19

Max Range: 3.5454. Min Range: -3.5454

Max Act: 3.4358. Min Act: -0.1700

Data Index: 1516463 (Python Code)

Max Activating Token Index: 246