Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1437 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.6707. Min Act: -0.1700

Data Index: 1550390 (Python Code)

Max Activating Token Index: 723

Text #1

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.5768. Min Act: -0.1700

Data Index: 1480491 (Python Code)

Max Activating Token Index: 821

Text #2

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.5141. Min Act: -0.1700

Data Index: 1388101 (Python Code)

Max Activating Token Index: 730

Text #3

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.5455. Min Act: -0.1700

Data Index: 1398451 (Python Code)

Max Activating Token Index: 821

Text #4

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4201. Min Act: -0.1700

Data Index: 1481250 (Python Code)

Max Activating Token Index: 291

Text #5

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4515. Min Act: -0.1700

Data Index: 1449201 (Python Code)

Max Activating Token Index: 192

Text #6

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4515. Min Act: -0.1700

Data Index: 1624472 (Python Code)

Max Activating Token Index: 762

Text #7

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4358. Min Act: -0.1700

Data Index: 1546000 (Python Code)

Max Activating Token Index: 714

Text #8

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4515. Min Act: -0.1700

Data Index: 1639870 (Python Code)

Max Activating Token Index: 926

Text #9

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4671. Min Act: -0.1700

Data Index: 1638805 (Python Code)

Max Activating Token Index: 812

Text #10

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4515. Min Act: -0.1700

Data Index: 1467791 (Python Code)

Max Activating Token Index: 602

Text #11

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4358. Min Act: -0.1700

Data Index: 1632807 (Python Code)

Max Activating Token Index: 728

Text #12

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4201. Min Act: -0.1700

Data Index: 1499554 (Python Code)

Max Activating Token Index: 525

Text #13

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.3887. Min Act: -0.1700

Data Index: 1631686 (Python Code)

Max Activating Token Index: 623

Text #14

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4358. Min Act: -0.1700

Data Index: 1602769 (Python Code)

Max Activating Token Index: 907

Text #15

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.3887. Min Act: -0.1700

Data Index: 1416208 (Python Code)

Max Activating Token Index: 94

Text #16

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.3887. Min Act: -0.1700

Data Index: 1556638 (Python Code)

Max Activating Token Index: 612

Text #17

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.3730. Min Act: -0.1700

Data Index: 1369079 (Python Code)

Max Activating Token Index: 337

Text #18

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4044. Min Act: -0.1700

Data Index: 1607214 (Python Code)

Max Activating Token Index: 852

Text #19

Max Range: 3.6707. Min Range: -3.6707

Max Act: 3.4044. Min Act: -0.1700

Data Index: 1368279 (Python Code)

Max Activating Token Index: 681