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

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

Neuron 1506 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.8079. Min Act: -0.1700

Data Index: 1417602 (Python Code)

Max Activating Token Index: 45

Text #1

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.8392. Min Act: -0.1700

Data Index: 1368914 (Python Code)

Max Activating Token Index: 782

Text #2

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.7453. Min Act: -0.1700

Data Index: 1476677 (Python Code)

Max Activating Token Index: 853

Text #3

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.7453. Min Act: -0.1700

Data Index: 1479778 (Python Code)

Max Activating Token Index: 761

Text #4

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.7453. Min Act: -0.1700

Data Index: 1365690 (Python Code)

Max Activating Token Index: 734

Text #5

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.7140. Min Act: -0.1700

Data Index: 1517390 (Python Code)

Max Activating Token Index: 1005

Text #6

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.6515. Min Act: -0.1700

Data Index: 1461269 (Python Code)

Max Activating Token Index: 882

Text #7

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.6515. Min Act: -0.1700

Data Index: 1618609 (Python Code)

Max Activating Token Index: 933

Text #8

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.6515. Min Act: -0.1700

Data Index: 1435324 (Python Code)

Max Activating Token Index: 878

Text #9

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.6045. Min Act: -0.1700

Data Index: 1446706 (Python Code)

Max Activating Token Index: 728

Text #10

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.6201. Min Act: -0.1700

Data Index: 1378734 (Python Code)

Max Activating Token Index: 336

Text #11

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.6201. Min Act: -0.1700

Data Index: 1405759 (Python Code)

Max Activating Token Index: 105

Text #12

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.6045. Min Act: -0.1700

Data Index: 1483118 (Python Code)

Max Activating Token Index: 737

Text #13

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.5888. Min Act: -0.1700

Data Index: 1560393 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.5732. Min Act: -0.1700

Data Index: 1407788 (Python Code)

Max Activating Token Index: 622

Text #15

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.5575. Min Act: -0.1700

Data Index: 1505349 (Python Code)

Max Activating Token Index: 377

Text #16

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.5575. Min Act: -0.1700

Data Index: 1538974 (Python Code)

Max Activating Token Index: 34

Text #17

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.5732. Min Act: -0.1700

Data Index: 1465240 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.5262. Min Act: -0.1700

Data Index: 1449103 (Python Code)

Max Activating Token Index: 808

Text #19

Max Range: 3.8392. Min Range: -3.8392

Max Act: 3.4948. Min Act: -0.1700

Data Index: 1521276 (Python Code)

Max Activating Token Index: 854