Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1497 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2955. Min Range: -1.2955

Max Act: 1.2955. Min Act: -0.0001

Data Index: 1427914 (Python Code)

Max Activating Token Index: 11

Text #1

Max Range: 1.2955. Min Range: -1.2955

Max Act: 1.2356. Min Act: -0.0001

Data Index: 1510027 (Python Code)

Max Activating Token Index: 245

Text #2

Max Range: 1.2955. Min Range: -1.2955

Max Act: 1.1871. Min Act: -0.0001

Data Index: 1398087 (Python Code)

Max Activating Token Index: 395

Text #3

Max Range: 1.2955. Min Range: -1.2955

Max Act: 1.0968. Min Act: -0.0001

Data Index: 1623705 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 1.2955. Min Range: -1.2955

Max Act: 1.0779. Min Act: -0.0001

Data Index: 1527621 (Python Code)

Max Activating Token Index: 5

Text #5

Max Range: 1.2955. Min Range: -1.2955

Max Act: 1.0779. Min Act: -0.0001

Data Index: 1443261 (Python Code)

Max Activating Token Index: 5

Text #6

Max Range: 1.2955. Min Range: -1.2955

Max Act: 1.1021. Min Act: -0.0001

Data Index: 1393541 (Python Code)

Max Activating Token Index: 594

Text #7

Max Range: 1.2955. Min Range: -1.2955

Max Act: 1.1783. Min Act: -0.0001

Data Index: 1408409 (Python Code)

Max Activating Token Index: 696

Text #8

Max Range: 1.2955. Min Range: -1.2955

Max Act: 0.9806. Min Act: -0.0001

Data Index: 1627533 (Python Code)

Max Activating Token Index: 42

Text #9

Max Range: 1.2955. Min Range: -1.2955

Max Act: 0.9598. Min Act: -0.0001

Data Index: 1494473 (Python Code)

Max Activating Token Index: 621

Text #10

Max Range: 1.2955. Min Range: -1.2955

Max Act: 1.1136. Min Act: -0.0001

Data Index: 1396556 (Python Code)

Max Activating Token Index: 26

Text #11

Max Range: 1.2955. Min Range: -1.2955

Max Act: 1.0467. Min Act: -0.0001

Data Index: 1470966 (Python Code)

Max Activating Token Index: 13

Text #12

Max Range: 1.2955. Min Range: -1.2955

Max Act: 0.9127. Min Act: -0.0001

Data Index: 1426290 (Python Code)

Max Activating Token Index: 789

Text #13

Max Range: 1.2955. Min Range: -1.2955

Max Act: 1.0427. Min Act: -0.0001

Data Index: 1364171 (Python Code)

Max Activating Token Index: 42

Text #14

Max Range: 1.2955. Min Range: -1.2955

Max Act: 0.9965. Min Act: -0.0001

Data Index: 1640586 (Python Code)

Max Activating Token Index: 94

Text #15

Max Range: 1.2955. Min Range: -1.2955

Max Act: 0.9682. Min Act: -0.0001

Data Index: 1405946 (Python Code)

Max Activating Token Index: 661

Text #16

Max Range: 1.2955. Min Range: -1.2955

Max Act: 1.0694. Min Act: -0.0001

Data Index: 1505686 (Python Code)

Max Activating Token Index: 946

Text #17

Max Range: 1.2955. Min Range: -1.2955

Max Act: 1.0118. Min Act: -0.0001

Data Index: 1410439 (Python Code)

Max Activating Token Index: 17

Text #18

Max Range: 1.2955. Min Range: -1.2955

Max Act: 0.9615. Min Act: -0.0001

Data Index: 1491757 (Python Code)

Max Activating Token Index: 8

Text #19

Max Range: 1.2955. Min Range: -1.2955

Max Act: 0.9347. Min Act: -0.0001

Data Index: 1487701 (Python Code)

Max Activating Token Index: 116