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

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

Neuron 938 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: 4.1144. Min Range: -4.1144

Max Act: 4.1144. Min Act: -0.1700

Data Index: 983921 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.8642. Min Act: -0.1700

Data Index: 511186 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.8955. Min Act: -0.1700

Data Index: 1417535 (Python Code)

Max Activating Token Index: 37

Text #3

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.8330. Min Act: -0.1700

Data Index: 1481436 (Python Code)

Max Activating Token Index: 37

Text #4

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.8330. Min Act: -0.1700

Data Index: 1502070 (Python Code)

Max Activating Token Index: 37

Text #5

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.8642. Min Act: -0.1700

Data Index: 1382869 (Python Code)

Max Activating Token Index: 37

Text #6

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.8330. Min Act: -0.1700

Data Index: 1604721 (Python Code)

Max Activating Token Index: 50

Text #7

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.8017. Min Act: -0.1700

Data Index: 1622881 (Python Code)

Max Activating Token Index: 37

Text #8

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.8642. Min Act: -0.1700

Data Index: 1553950 (Python Code)

Max Activating Token Index: 600

Text #9

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.8017. Min Act: -0.1700

Data Index: 1538871 (Python Code)

Max Activating Token Index: 36

Text #10

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.8017. Min Act: -0.1700

Data Index: 1628350 (Python Code)

Max Activating Token Index: 36

Text #11

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.8017. Min Act: -0.1700

Data Index: 1419719 (Python Code)

Max Activating Token Index: 69

Text #12

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.8017. Min Act: -0.1700

Data Index: 1478449 (Python Code)

Max Activating Token Index: 50

Text #13

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.8017. Min Act: -0.1700

Data Index: 1651065 (Python Code)

Max Activating Token Index: 37

Text #14

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.7704. Min Act: -0.1700

Data Index: 1448684 (Python Code)

Max Activating Token Index: 70

Text #15

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.8017. Min Act: -0.1700

Data Index: 1439221 (Python Code)

Max Activating Token Index: 70

Text #16

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.7704. Min Act: -0.1700

Data Index: 1592345 (Python Code)

Max Activating Token Index: 53

Text #17

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.8017. Min Act: -0.1700

Data Index: 1567645 (Python Code)

Max Activating Token Index: 37

Text #18

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.8017. Min Act: -0.1700

Data Index: 1556366 (Python Code)

Max Activating Token Index: 70

Text #19

Max Range: 4.1144. Min Range: -4.1144

Max Act: 3.7704. Min Act: -0.1700

Data Index: 1472512 (Python Code)

Max Activating Token Index: 49