Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1422 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.8344. Min Range: -5.8344

Max Act: 5.8344. Min Act: -0.1700

Data Index: 1404939 (Python Code)

Max Activating Token Index: 23

Text #1

Max Range: 5.8344. Min Range: -5.8344

Max Act: 5.8344. Min Act: -0.1700

Data Index: 1600422 (Python Code)

Max Activating Token Index: 23

Text #2

Max Range: 5.8344. Min Range: -5.8344

Max Act: 5.6157. Min Act: -0.1699

Data Index: 1501640 (Python Code)

Max Activating Token Index: 20

Text #3

Max Range: 5.8344. Min Range: -5.8344

Max Act: 5.6469. Min Act: -0.1700

Data Index: 1461648 (Python Code)

Max Activating Token Index: 20

Text #4

Max Range: 5.8344. Min Range: -5.8344

Max Act: 5.6157. Min Act: -0.1700

Data Index: 1640612 (Python Code)

Max Activating Token Index: 20

Text #5

Max Range: 5.8344. Min Range: -5.8344

Max Act: 5.6469. Min Act: -0.1700

Data Index: 1582971 (Python Code)

Max Activating Token Index: 20

Text #6

Max Range: 5.8344. Min Range: -5.8344

Max Act: 5.6157. Min Act: -0.1700

Data Index: 1469674 (Python Code)

Max Activating Token Index: 20

Text #7

Max Range: 5.8344. Min Range: -5.8344

Max Act: 5.6469. Min Act: -0.1700

Data Index: 1393089 (Python Code)

Max Activating Token Index: 12

Text #8

Max Range: 5.8344. Min Range: -5.8344

Max Act: 5.6782. Min Act: -0.1699

Data Index: 1593904 (Python Code)

Max Activating Token Index: 65

Text #9

Max Range: 5.8344. Min Range: -5.8344

Max Act: 5.6469. Min Act: -0.1700

Data Index: 1577106 (Python Code)

Max Activating Token Index: 42

Text #10

Max Range: 5.8344. Min Range: -5.8344

Max Act: 5.6782. Min Act: -0.1700

Data Index: 1511717 (Python Code)

Max Activating Token Index: 11

Text #11

Max Range: 5.8344. Min Range: -5.8344

Max Act: 5.6157. Min Act: -0.1700

Data Index: 1520002 (Python Code)

Max Activating Token Index: 37

Text #12

Max Range: 5.8344. Min Range: -5.8344

Max Act: 5.5844. Min Act: -0.1700

Data Index: 1501740 (Python Code)

Max Activating Token Index: 47

Text #13

Max Range: 5.8344. Min Range: -5.8344

Max Act: 5.6469. Min Act: -0.1700

Data Index: 1622194 (Python Code)

Max Activating Token Index: 87

Text #14

Max Range: 5.8344. Min Range: -5.8344

Max Act: 5.6782. Min Act: -0.1700

Data Index: 1523663 (Python Code)

Max Activating Token Index: 16

Text #15

Max Range: 5.8344. Min Range: -5.8344

Max Act: 5.6157. Min Act: -0.1700

Data Index: 1524978 (Python Code)

Max Activating Token Index: 27

Text #16

Max Range: 5.8344. Min Range: -5.8344

Max Act: 5.5844. Min Act: -0.1700

Data Index: 1585554 (Python Code)

Max Activating Token Index: 8

Text #17

Max Range: 5.8344. Min Range: -5.8344

Max Act: 5.6157. Min Act: -0.1700

Data Index: 1451901 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 5.8344. Min Range: -5.8344

Max Act: 5.5844. Min Act: -0.1700

Data Index: 1395727 (Python Code)

Max Activating Token Index: 8

Text #19

Max Range: 5.8344. Min Range: -5.8344

Max Act: 5.5844. Min Act: -0.1700

Data Index: 1580947 (Python Code)

Max Activating Token Index: 8