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

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

Neuron 886 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: 3.3218. Min Range: -3.3218

Max Act: 3.3218. Min Act: -0.1700

Data Index: 1620631 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 3.3218. Min Range: -3.3218

Max Act: 3.2904. Min Act: -0.1700

Data Index: 1459016 (Python Code)

Max Activating Token Index: 4

Text #2

Max Range: 3.3218. Min Range: -3.3218

Max Act: 3.2904. Min Act: -0.1700

Data Index: 1452409 (Python Code)

Max Activating Token Index: 4

Text #3

Max Range: 3.3218. Min Range: -3.3218

Max Act: 3.2590. Min Act: -0.1700

Data Index: 1597688 (Python Code)

Max Activating Token Index: 4

Text #4

Max Range: 3.3218. Min Range: -3.3218

Max Act: 3.1961. Min Act: -0.1700

Data Index: 1407186 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.3218. Min Range: -3.3218

Max Act: 3.1961. Min Act: -0.1700

Data Index: 1516175 (Python Code)

Max Activating Token Index: 13

Text #6

Max Range: 3.3218. Min Range: -3.3218

Max Act: 3.1646. Min Act: -0.1700

Data Index: 1589664 (Python Code)

Max Activating Token Index: 2

Text #7

Max Range: 3.3218. Min Range: -3.3218

Max Act: 3.1646. Min Act: -0.1677

Data Index: 1415689 (Python Code)

Max Activating Token Index: 11

Text #8

Max Range: 3.3218. Min Range: -3.3218

Max Act: 3.1961. Min Act: -0.1700

Data Index: 1486068 (Python Code)

Max Activating Token Index: 6

Text #9

Max Range: 3.3218. Min Range: -3.3218

Max Act: 3.1961. Min Act: -0.1700

Data Index: 1515359 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 3.3218. Min Range: -3.3218

Max Act: 3.1961. Min Act: -0.1699

Data Index: 1361499 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 3.3218. Min Range: -3.3218

Max Act: 3.1961. Min Act: -0.1699

Data Index: 1597107 (Python Code)

Max Activating Token Index: 21

Text #12

Max Range: 3.3218. Min Range: -3.3218

Max Act: 3.1646. Min Act: -0.1700

Data Index: 1368070 (Python Code)

Max Activating Token Index: 5

Text #13

Max Range: 3.3218. Min Range: -3.3218

Max Act: 3.1646. Min Act: -0.1700

Data Index: 1509642 (Python Code)

Max Activating Token Index: 6

Text #14

Max Range: 3.3218. Min Range: -3.3218

Max Act: 3.1646. Min Act: -0.1700

Data Index: 1532322 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 3.3218. Min Range: -3.3218

Max Act: 3.1331. Min Act: -0.1700

Data Index: 1498230 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 3.3218. Min Range: -3.3218

Max Act: 3.1646. Min Act: -0.1700

Data Index: 1514404 (Python Code)

Max Activating Token Index: 3

Text #17

Max Range: 3.3218. Min Range: -3.3218

Max Act: 3.1646. Min Act: -0.1700

Data Index: 1557447 (Python Code)

Max Activating Token Index: 6

Text #18

Max Range: 3.3218. Min Range: -3.3218

Max Act: 3.1331. Min Act: -0.1700

Data Index: 1388501 (Python Code)

Max Activating Token Index: 2

Text #19

Max Range: 3.3218. Min Range: -3.3218

Max Act: 3.1331. Min Act: -0.1700

Data Index: 1505724 (Python Code)

Max Activating Token Index: 3