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

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

Neuron 1518 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: 5.1565. Min Range: -5.1565

Max Act: 5.1565. Min Act: -0.1700

Data Index: 1574789 (Python Code)

Max Activating Token Index: 74

Text #1

Max Range: 5.1565. Min Range: -5.1565

Max Act: 5.0002. Min Act: -0.1700

Data Index: 1511884 (Python Code)

Max Activating Token Index: 22

Text #2

Max Range: 5.1565. Min Range: -5.1565

Max Act: 5.0315. Min Act: -0.1700

Data Index: 1638316 (Python Code)

Max Activating Token Index: 23

Text #3

Max Range: 5.1565. Min Range: -5.1565

Max Act: 5.0315. Min Act: -0.1700

Data Index: 1464097 (Python Code)

Max Activating Token Index: 25

Text #4

Max Range: 5.1565. Min Range: -5.1565

Max Act: 4.9377. Min Act: -0.1700

Data Index: 1637578 (Python Code)

Max Activating Token Index: 71

Text #5

Max Range: 5.1565. Min Range: -5.1565

Max Act: 4.9690. Min Act: -0.1700

Data Index: 1399089 (Python Code)

Max Activating Token Index: 26

Text #6

Max Range: 5.1565. Min Range: -5.1565

Max Act: 4.9377. Min Act: -0.1700

Data Index: 1524127 (Python Code)

Max Activating Token Index: 42

Text #7

Max Range: 5.1565. Min Range: -5.1565

Max Act: 4.9690. Min Act: -0.1700

Data Index: 1643475 (Python Code)

Max Activating Token Index: 26

Text #8

Max Range: 5.1565. Min Range: -5.1565

Max Act: 4.9690. Min Act: -0.1700

Data Index: 1409557 (Python Code)

Max Activating Token Index: 37

Text #9

Max Range: 5.1565. Min Range: -5.1565

Max Act: 4.9065. Min Act: -0.1700

Data Index: 1435824 (Python Code)

Max Activating Token Index: 874

Text #10

Max Range: 5.1565. Min Range: -5.1565

Max Act: 4.8440. Min Act: -0.1700

Data Index: 1420677 (Python Code)

Max Activating Token Index: 756

Text #11

Max Range: 5.1565. Min Range: -5.1565

Max Act: 4.8752. Min Act: -0.1700

Data Index: 1470561 (Python Code)

Max Activating Token Index: 40

Text #12

Max Range: 5.1565. Min Range: -5.1565

Max Act: 4.9065. Min Act: -0.1700

Data Index: 1603921 (Python Code)

Max Activating Token Index: 77

Text #13

Max Range: 5.1565. Min Range: -5.1565

Max Act: 4.9377. Min Act: -0.1700

Data Index: 1613504 (Python Code)

Max Activating Token Index: 33

Text #14

Max Range: 5.1565. Min Range: -5.1565

Max Act: 4.8440. Min Act: -0.1700

Data Index: 1588728 (Python Code)

Max Activating Token Index: 105

Text #15

Max Range: 5.1565. Min Range: -5.1565

Max Act: 4.9377. Min Act: -0.1700

Data Index: 1542127 (Python Code)

Max Activating Token Index: 84

Text #16

Max Range: 5.1565. Min Range: -5.1565

Max Act: 4.8440. Min Act: -0.1700

Data Index: 1632748 (Python Code)

Max Activating Token Index: 82

Text #17

Max Range: 5.1565. Min Range: -5.1565

Max Act: 4.8440. Min Act: -0.1700

Data Index: 1626506 (Python Code)

Max Activating Token Index: 155

Text #18

Max Range: 5.1565. Min Range: -5.1565

Max Act: 4.9065. Min Act: -0.1700

Data Index: 1486308 (Python Code)

Max Activating Token Index: 56

Text #19

Max Range: 5.1565. Min Range: -5.1565

Max Act: 4.9065. Min Act: -0.1700

Data Index: 1536243 (Python Code)

Max Activating Token Index: 25