Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4406 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.4666. Min Act: -0.0000

Data Index: 1432838 (Python Code)

Max Activating Token Index: 19

Text #1

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.4176. Min Act: -0.0001

Data Index: 1638470 (Python Code)

Max Activating Token Index: 379

Text #2

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.4169. Min Act: -0.0000

Data Index: 1464529 (Python Code)

Max Activating Token Index: 960

Text #3

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.4160. Min Act: -0.0000

Data Index: 1510931 (Python Code)

Max Activating Token Index: 246

Text #4

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3966. Min Act: -0.0001

Data Index: 1610896 (Python Code)

Max Activating Token Index: 585

Text #5

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3768. Min Act: -0.0000

Data Index: 1492256 (Python Code)

Max Activating Token Index: 187

Text #6

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3764. Min Act: -0.0000

Data Index: 1452329 (Python Code)

Max Activating Token Index: 163

Text #7

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3729. Min Act: -0.0000

Data Index: 1621691 (Python Code)

Max Activating Token Index: 785

Text #8

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3806. Min Act: -0.0000

Data Index: 1443063 (Python Code)

Max Activating Token Index: 480

Text #9

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3924. Min Act: -0.0000

Data Index: 1395698 (Python Code)

Max Activating Token Index: 878

Text #10

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3802. Min Act: -0.0000

Data Index: 1521014 (Python Code)

Max Activating Token Index: 243

Text #11

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3762. Min Act: -0.0000

Data Index: 1444546 (Python Code)

Max Activating Token Index: 29

Text #12

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3757. Min Act: -0.0001

Data Index: 1570170 (Python Code)

Max Activating Token Index: 55

Text #13

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3639. Min Act: -0.0000

Data Index: 1391350 (Python Code)

Max Activating Token Index: 369

Text #14

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3491. Min Act: -0.0000

Data Index: 1464019 (Python Code)

Max Activating Token Index: 843

Text #15

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3584. Min Act: -0.0000

Data Index: 1562559 (Python Code)

Max Activating Token Index: 32

Text #16

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3818. Min Act: -0.0001

Data Index: 1508547 (Python Code)

Max Activating Token Index: 17

Text #17

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3560. Min Act: -0.0000

Data Index: 1411259 (Python Code)

Max Activating Token Index: 102

Text #18

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3558. Min Act: -0.0000

Data Index: 1427081 (Python Code)

Max Activating Token Index: 310

Text #19

Max Range: 0.4666. Min Range: -0.4666

Max Act: 0.3727. Min Act: -0.0000

Data Index: 1411801 (Python Code)

Max Activating Token Index: 91