Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1398 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.7393. Min Act: -0.0001

Data Index: 1655801 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.7136. Min Act: -0.0001

Data Index: 1487918 (Python Code)

Max Activating Token Index: 8

Text #2

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.6839. Min Act: -0.0001

Data Index: 1398365 (Python Code)

Max Activating Token Index: 15

Text #3

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.6298. Min Act: -0.0001

Data Index: 1448025 (Python Code)

Max Activating Token Index: 12

Text #4

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.6237. Min Act: -0.0001

Data Index: 1543748 (Python Code)

Max Activating Token Index: 21

Text #5

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.5994. Min Act: -0.0001

Data Index: 1614902 (Python Code)

Max Activating Token Index: 775

Text #6

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.6047. Min Act: -0.0001

Data Index: 1644306 (Python Code)

Max Activating Token Index: 927

Text #7

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.5583. Min Act: -0.0001

Data Index: 1544423 (Python Code)

Max Activating Token Index: 11

Text #8

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.5563. Min Act: -0.0001

Data Index: 1436752 (Python Code)

Max Activating Token Index: 11

Text #9

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.5937. Min Act: -0.0001

Data Index: 1516867 (Python Code)

Max Activating Token Index: 968

Text #10

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.5272. Min Act: -0.0001

Data Index: 1365819 (Python Code)

Max Activating Token Index: 63

Text #11

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.5200. Min Act: -0.0001

Data Index: 1460139 (Python Code)

Max Activating Token Index: 108

Text #12

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.5345. Min Act: -0.0001

Data Index: 1365840 (Python Code)

Max Activating Token Index: 5

Text #13

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.5157. Min Act: -0.0001

Data Index: 1417563 (Python Code)

Max Activating Token Index: 483

Text #14

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.5076. Min Act: -0.0001

Data Index: 1411949 (Python Code)

Max Activating Token Index: 169

Text #15

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.5017. Min Act: -0.0001

Data Index: 1370901 (Python Code)

Max Activating Token Index: 32

Text #16

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.4878. Min Act: -0.0001

Data Index: 1599391 (Python Code)

Max Activating Token Index: 10

Text #17

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.4842. Min Act: -0.0001

Data Index: 1618357 (Python Code)

Max Activating Token Index: 22

Text #18

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.4827. Min Act: -0.0001

Data Index: 1450965 (Python Code)

Max Activating Token Index: 8

Text #19

Max Range: 0.7393. Min Range: -0.7393

Max Act: 0.4503. Min Act: -0.0001

Data Index: 1370982 (Python Code)

Max Activating Token Index: 38