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

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

Neuron 941 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: 3.1050. Min Range: -3.1050

Max Act: 3.1050. Min Act: -0.1700

Data Index: 1467362 (Python Code)

Max Activating Token Index: 2

Text #1

Max Range: 3.1050. Min Range: -3.1050

Max Act: 3.1050. Min Act: -0.1699

Data Index: 1452446 (Python Code)

Max Activating Token Index: 2

Text #2

Max Range: 3.1050. Min Range: -3.1050

Max Act: 3.0892. Min Act: -0.1700

Data Index: 259656 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 3.1050. Min Range: -3.1050

Max Act: 3.0734. Min Act: -0.1700

Data Index: 1283619 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 3.1050. Min Range: -3.1050

Max Act: 3.0734. Min Act: -0.1700

Data Index: 1444979 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 3.1050. Min Range: -3.1050

Max Act: 3.0734. Min Act: -0.1699

Data Index: 1497848 (Python Code)

Max Activating Token Index: 4

Text #6

Max Range: 3.1050. Min Range: -3.1050

Max Act: 3.0734. Min Act: -0.1700

Data Index: 1530705 (Python Code)

Max Activating Token Index: 4

Text #7

Max Range: 3.1050. Min Range: -3.1050

Max Act: 3.0418. Min Act: -0.1700

Data Index: 1564760 (Python Code)

Max Activating Token Index: 11

Text #8

Max Range: 3.1050. Min Range: -3.1050

Max Act: 3.0261. Min Act: -0.1700

Data Index: 1645099 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 3.1050. Min Range: -3.1050

Max Act: 3.0418. Min Act: -0.1700

Data Index: 1363828 (Python Code)

Max Activating Token Index: 5

Text #10

Max Range: 3.1050. Min Range: -3.1050

Max Act: 3.0418. Min Act: -0.1700

Data Index: 1536626 (Python Code)

Max Activating Token Index: 5

Text #11

Max Range: 3.1050. Min Range: -3.1050

Max Act: 3.0418. Min Act: -0.1700

Data Index: 1580569 (Python Code)

Max Activating Token Index: 5

Text #12

Max Range: 3.1050. Min Range: -3.1050

Max Act: 3.0418. Min Act: -0.1700

Data Index: 1424243 (Python Code)

Max Activating Token Index: 7

Text #13

Max Range: 3.1050. Min Range: -3.1050

Max Act: 3.0418. Min Act: -0.1700

Data Index: 1507806 (Python Code)

Max Activating Token Index: 7

Text #14

Max Range: 3.1050. Min Range: -3.1050

Max Act: 2.9786. Min Act: -0.1700

Data Index: 1527761 (Python Code)

Max Activating Token Index: 11

Text #15

Max Range: 3.1050. Min Range: -3.1050

Max Act: 2.9628. Min Act: -0.1700

Data Index: 1365183 (Python Code)

Max Activating Token Index: 10

Text #16

Max Range: 3.1050. Min Range: -3.1050

Max Act: 2.9470. Min Act: -0.1700

Data Index: 1497834 (Python Code)

Max Activating Token Index: 4

Text #17

Max Range: 3.1050. Min Range: -3.1050

Max Act: 2.9470. Min Act: -0.1700

Data Index: 1446428 (Python Code)

Max Activating Token Index: 16

Text #18

Max Range: 3.1050. Min Range: -3.1050

Max Act: 2.9470. Min Act: -0.1700

Data Index: 1463235 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 3.1050. Min Range: -3.1050

Max Act: 2.9470. Min Act: -0.1700

Data Index: 1562794 (Python Code)

Max Activating Token Index: 21