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

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

Neuron 356 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.6737. Min Act: -0.1700

Data Index: 1528032 (Python Code)

Max Activating Token Index: 438

Text #1

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.6111. Min Act: -0.1700

Data Index: 1382911 (Python Code)

Max Activating Token Index: 13

Text #2

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.5798. Min Act: -0.1700

Data Index: 1648145 (Python Code)

Max Activating Token Index: 54

Text #3

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.5485. Min Act: -0.1700

Data Index: 1589608 (Python Code)

Max Activating Token Index: 12

Text #4

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.5485. Min Act: -0.1700

Data Index: 1601085 (Python Code)

Max Activating Token Index: 22

Text #5

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.5485. Min Act: -0.1700

Data Index: 1379975 (Python Code)

Max Activating Token Index: 58

Text #6

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.5798. Min Act: -0.1700

Data Index: 1503795 (Python Code)

Max Activating Token Index: 125

Text #7

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.5172. Min Act: -0.1700

Data Index: 1391143 (Python Code)

Max Activating Token Index: 17

Text #8

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.5172. Min Act: -0.1699

Data Index: 1649076 (Python Code)

Max Activating Token Index: 60

Text #9

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.5172. Min Act: -0.1700

Data Index: 1473860 (Python Code)

Max Activating Token Index: 26

Text #10

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.5172. Min Act: -0.1700

Data Index: 1606247 (Python Code)

Max Activating Token Index: 9

Text #11

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.5172. Min Act: -0.1700

Data Index: 1445913 (Python Code)

Max Activating Token Index: 27

Text #12

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.5172. Min Act: -0.1700

Data Index: 1499146 (Python Code)

Max Activating Token Index: 10

Text #13

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4858. Min Act: -0.1700

Data Index: 1459541 (Python Code)

Max Activating Token Index: 20

Text #14

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4858. Min Act: -0.1700

Data Index: 1433941 (Python Code)

Max Activating Token Index: 13

Text #15

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4858. Min Act: -0.1700

Data Index: 1394492 (Python Code)

Max Activating Token Index: 36

Text #16

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4858. Min Act: -0.1700

Data Index: 1610235 (Python Code)

Max Activating Token Index: 57

Text #17

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4858. Min Act: -0.1700

Data Index: 1580041 (Python Code)

Max Activating Token Index: 18

Text #18

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4858. Min Act: -0.1700

Data Index: 1559357 (Python Code)

Max Activating Token Index: 9

Text #19

Max Range: 3.6737. Min Range: -3.6737

Max Act: 3.4545. Min Act: -0.1700

Data Index: 1453244 (Python Code)

Max Activating Token Index: 419