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

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

Neuron 664 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: 3.6697. Min Range: -3.6697

Max Act: 3.6697. Min Act: -0.1700

Data Index: 1429930 (Python Code)

Max Activating Token Index: 948

Text #1

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.6227. Min Act: -0.1700

Data Index: 1534853 (Python Code)

Max Activating Token Index: 417

Text #2

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.6227. Min Act: -0.1700

Data Index: 1591515 (Python Code)

Max Activating Token Index: 618

Text #3

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.6227. Min Act: -0.1700

Data Index: 1587723 (Python Code)

Max Activating Token Index: 153

Text #4

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.5914. Min Act: -0.1700

Data Index: 1436000 (Python Code)

Max Activating Token Index: 733

Text #5

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.6070. Min Act: -0.1700

Data Index: 1515307 (Python Code)

Max Activating Token Index: 140

Text #6

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.5601. Min Act: -0.1700

Data Index: 1605378 (Python Code)

Max Activating Token Index: 937

Text #7

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.5444. Min Act: -0.1700

Data Index: 1502619 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.5131. Min Act: -0.1700

Data Index: 1639762 (Python Code)

Max Activating Token Index: 207

Text #9

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.5287. Min Act: -0.1700

Data Index: 1545944 (Python Code)

Max Activating Token Index: 81

Text #10

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.5287. Min Act: -0.1700

Data Index: 1401950 (Python Code)

Max Activating Token Index: 994

Text #11

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.4974. Min Act: -0.1700

Data Index: 1613649 (Python Code)

Max Activating Token Index: 199

Text #12

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.4817. Min Act: -0.1700

Data Index: 1511513 (Python Code)

Max Activating Token Index: 998

Text #13

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.5131. Min Act: -0.1700

Data Index: 1520794 (Python Code)

Max Activating Token Index: 648

Text #14

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.5131. Min Act: -0.1700

Data Index: 1139333 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.4661. Min Act: -0.1700

Data Index: 1369659 (Python Code)

Max Activating Token Index: 650

Text #16

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.4661. Min Act: -0.1700

Data Index: 1654624 (Python Code)

Max Activating Token Index: 905

Text #17

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.4974. Min Act: -0.1700

Data Index: 1635634 (Python Code)

Max Activating Token Index: 101

Text #18

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.4504. Min Act: -0.1700

Data Index: 1516783 (Python Code)

Max Activating Token Index: 79

Text #19

Max Range: 3.6697. Min Range: -3.6697

Max Act: 3.4504. Min Act: -0.1700

Data Index: 1432530 (Python Code)

Max Activating Token Index: 149