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

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

Neuron 1066 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: 3.4645. Min Range: -3.4645

Max Act: 3.4645. Min Act: -0.1700

Data Index: 1498066 (Python Code)

Max Activating Token Index: 11

Text #1

Max Range: 3.4645. Min Range: -3.4645

Max Act: 3.3704. Min Act: -0.1700

Data Index: 1649746 (Python Code)

Max Activating Token Index: 11

Text #2

Max Range: 3.4645. Min Range: -3.4645

Max Act: 3.3390. Min Act: -0.1700

Data Index: 1463064 (Python Code)

Max Activating Token Index: 17

Text #3

Max Range: 3.4645. Min Range: -3.4645

Max Act: 3.3076. Min Act: -0.1700

Data Index: 1635680 (Python Code)

Max Activating Token Index: 8

Text #4

Max Range: 3.4645. Min Range: -3.4645

Max Act: 3.2919. Min Act: -0.1700

Data Index: 1526165 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 3.4645. Min Range: -3.4645

Max Act: 3.2762. Min Act: -0.1700

Data Index: 1444213 (Python Code)

Max Activating Token Index: 4

Text #6

Max Range: 3.4645. Min Range: -3.4645

Max Act: 3.2291. Min Act: -0.1700

Data Index: 1635979 (Python Code)

Max Activating Token Index: 26

Text #7

Max Range: 3.4645. Min Range: -3.4645

Max Act: 3.2448. Min Act: -0.1700

Data Index: 1471498 (Python Code)

Max Activating Token Index: 730

Text #8

Max Range: 3.4645. Min Range: -3.4645

Max Act: 3.2291. Min Act: -0.1700

Data Index: 1371288 (Python Code)

Max Activating Token Index: 851

Text #9

Max Range: 3.4645. Min Range: -3.4645

Max Act: 3.2291. Min Act: -0.1700

Data Index: 1491134 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 3.4645. Min Range: -3.4645

Max Act: 3.2133. Min Act: -0.1700

Data Index: 1603159 (Python Code)

Max Activating Token Index: 683

Text #11

Max Range: 3.4645. Min Range: -3.4645

Max Act: 3.2133. Min Act: -0.1700

Data Index: 1380951 (Python Code)

Max Activating Token Index: 47

Text #12

Max Range: 3.4645. Min Range: -3.4645

Max Act: 3.2133. Min Act: -0.1700

Data Index: 1552436 (Python Code)

Max Activating Token Index: 12

Text #13

Max Range: 3.4645. Min Range: -3.4645

Max Act: 3.2133. Min Act: -0.1700

Data Index: 1578215 (Python Code)

Max Activating Token Index: 512

Text #14

Max Range: 3.4645. Min Range: -3.4645

Max Act: 3.1976. Min Act: -0.1700

Data Index: 1627441 (Python Code)

Max Activating Token Index: 13

Text #15

Max Range: 3.4645. Min Range: -3.4645

Max Act: 3.1976. Min Act: -0.1700

Data Index: 1406373 (Python Code)

Max Activating Token Index: 158

Text #16

Max Range: 3.4645. Min Range: -3.4645

Max Act: 3.1976. Min Act: -0.1700

Data Index: 1366883 (Python Code)

Max Activating Token Index: 34

Text #17

Max Range: 3.4645. Min Range: -3.4645

Max Act: 3.1819. Min Act: -0.1700

Data Index: 1383108 (Python Code)

Max Activating Token Index: 9

Text #18

Max Range: 3.4645. Min Range: -3.4645

Max Act: 3.1976. Min Act: -0.1700

Data Index: 1472987 (Python Code)

Max Activating Token Index: 886

Text #19

Max Range: 3.4645. Min Range: -3.4645

Max Act: 3.1661. Min Act: -0.1700

Data Index: 1519697 (Python Code)

Max Activating Token Index: 548