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

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

Neuron 1890 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: 7.1456. Min Range: -7.1456

Max Act: 7.1456. Min Act: -0.1700

Data Index: 1590765 (Python Code)

Max Activating Token Index: 268

Text #1

Max Range: 7.1456. Min Range: -7.1456

Max Act: 7.0206. Min Act: -0.1700

Data Index: 1622063 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 7.1456. Min Range: -7.1456

Max Act: 6.9269. Min Act: -0.1700

Data Index: 1508978 (Python Code)

Max Activating Token Index: 449

Text #3

Max Range: 7.1456. Min Range: -7.1456

Max Act: 6.8331. Min Act: -0.1700

Data Index: 1593546 (Python Code)

Max Activating Token Index: 510

Text #4

Max Range: 7.1456. Min Range: -7.1456

Max Act: 6.8331. Min Act: -0.1700

Data Index: 1422723 (Python Code)

Max Activating Token Index: 21

Text #5

Max Range: 7.1456. Min Range: -7.1456

Max Act: 6.6769. Min Act: -0.1700

Data Index: 1579080 (Python Code)

Max Activating Token Index: 11

Text #6

Max Range: 7.1456. Min Range: -7.1456

Max Act: 6.7081. Min Act: -0.1700

Data Index: 1539964 (Python Code)

Max Activating Token Index: 47

Text #7

Max Range: 7.1456. Min Range: -7.1456

Max Act: 6.6456. Min Act: -0.1700

Data Index: 1611452 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 7.1456. Min Range: -7.1456

Max Act: 6.5831. Min Act: -0.1700

Data Index: 1434091 (Python Code)

Max Activating Token Index: 21

Text #9

Max Range: 7.1456. Min Range: -7.1456

Max Act: 6.5831. Min Act: -0.1700

Data Index: 1456998 (Python Code)

Max Activating Token Index: 49

Text #10

Max Range: 7.1456. Min Range: -7.1456

Max Act: 6.5519. Min Act: -0.1700

Data Index: 1395263 (Python Code)

Max Activating Token Index: 71

Text #11

Max Range: 7.1456. Min Range: -7.1456

Max Act: 6.4581. Min Act: -0.1700

Data Index: 1501178 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 7.1456. Min Range: -7.1456

Max Act: 6.4581. Min Act: -0.1700

Data Index: 1485767 (Python Code)

Max Activating Token Index: 39

Text #13

Max Range: 7.1456. Min Range: -7.1456

Max Act: 6.4581. Min Act: -0.1700

Data Index: 1531351 (Python Code)

Max Activating Token Index: 20

Text #14

Max Range: 7.1456. Min Range: -7.1456

Max Act: 6.4581. Min Act: -0.1700

Data Index: 1440464 (Python Code)

Max Activating Token Index: 22

Text #15

Max Range: 7.1456. Min Range: -7.1456

Max Act: 6.4581. Min Act: -0.1700

Data Index: 1433711 (Python Code)

Max Activating Token Index: 42

Text #16

Max Range: 7.1456. Min Range: -7.1456

Max Act: 6.4581. Min Act: -0.1700

Data Index: 1553991 (Python Code)

Max Activating Token Index: 70

Text #17

Max Range: 7.1456. Min Range: -7.1456

Max Act: 6.3956. Min Act: -0.1700

Data Index: 1572972 (Python Code)

Max Activating Token Index: 53

Text #18

Max Range: 7.1456. Min Range: -7.1456

Max Act: 6.3956. Min Act: -0.1700

Data Index: 1634536 (Python Code)

Max Activating Token Index: 897

Text #19

Max Range: 7.1456. Min Range: -7.1456

Max Act: 6.3644. Min Act: -0.1700

Data Index: 1370752 (Python Code)

Max Activating Token Index: 59