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

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

Neuron 1600 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.2727. Min Range: -5.2727

Max Act: 5.2414. Min Act: -0.1700

Data Index: 1411422 (Python Code)

Max Activating Token Index: 605

Text #1

Max Range: 5.2727. Min Range: -5.2727

Max Act: 5.2414. Min Act: -0.1700

Data Index: 1440491 (Python Code)

Max Activating Token Index: 107

Text #2

Max Range: 5.2727. Min Range: -5.2727

Max Act: 5.2727. Min Act: -0.1700

Data Index: 1502050 (Python Code)

Max Activating Token Index: 699

Text #3

Max Range: 5.2727. Min Range: -5.2727

Max Act: 5.2102. Min Act: -0.1700

Data Index: 1467934 (Python Code)

Max Activating Token Index: 580

Text #4

Max Range: 5.2727. Min Range: -5.2727

Max Act: 5.2414. Min Act: -0.1700

Data Index: 1575808 (Python Code)

Max Activating Token Index: 1020

Text #5

Max Range: 5.2727. Min Range: -5.2727

Max Act: 5.2102. Min Act: -0.1700

Data Index: 1542993 (Python Code)

Max Activating Token Index: 873

Text #6

Max Range: 5.2727. Min Range: -5.2727

Max Act: 5.1789. Min Act: -0.1700

Data Index: 1409091 (Python Code)

Max Activating Token Index: 169

Text #7

Max Range: 5.2727. Min Range: -5.2727

Max Act: 5.1789. Min Act: -0.1700

Data Index: 1447782 (Python Code)

Max Activating Token Index: 133

Text #8

Max Range: 5.2727. Min Range: -5.2727

Max Act: 5.2102. Min Act: -0.1700

Data Index: 1390135 (Python Code)

Max Activating Token Index: 80

Text #9

Max Range: 5.2727. Min Range: -5.2727

Max Act: 5.2102. Min Act: -0.1700

Data Index: 1569129 (Python Code)

Max Activating Token Index: 198

Text #10

Max Range: 5.2727. Min Range: -5.2727

Max Act: 5.2414. Min Act: -0.1700

Data Index: 1452746 (Python Code)

Max Activating Token Index: 29

Text #11

Max Range: 5.2727. Min Range: -5.2727

Max Act: 5.1789. Min Act: -0.1700

Data Index: 1421771 (Python Code)

Max Activating Token Index: 815

Text #12

Max Range: 5.2727. Min Range: -5.2727

Max Act: 5.1789. Min Act: -0.1700

Data Index: 1643736 (Python Code)

Max Activating Token Index: 110

Text #13

Max Range: 5.2727. Min Range: -5.2727

Max Act: 5.1164. Min Act: -0.1700

Data Index: 1498835 (Python Code)

Max Activating Token Index: 746

Text #14

Max Range: 5.2727. Min Range: -5.2727

Max Act: 5.1789. Min Act: -0.1700

Data Index: 1574488 (Python Code)

Max Activating Token Index: 48

Text #15

Max Range: 5.2727. Min Range: -5.2727

Max Act: 5.1789. Min Act: -0.1700

Data Index: 1375024 (Python Code)

Max Activating Token Index: 47

Text #16

Max Range: 5.2727. Min Range: -5.2727

Max Act: 5.1477. Min Act: -0.1700

Data Index: 1388379 (Python Code)

Max Activating Token Index: 121

Text #17

Max Range: 5.2727. Min Range: -5.2727

Max Act: 5.2102. Min Act: -0.1700

Data Index: 1416682 (Python Code)

Max Activating Token Index: 733

Text #18

Max Range: 5.2727. Min Range: -5.2727

Max Act: 5.1789. Min Act: -0.1700

Data Index: 1560867 (Python Code)

Max Activating Token Index: 217

Text #19

Max Range: 5.2727. Min Range: -5.2727

Max Act: 5.1789. Min Act: -0.1700

Data Index: 1640194 (Python Code)

Max Activating Token Index: 229