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

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

Neuron 1290 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0987. Min Act: -0.0001

Data Index: 1651355 (Python Code)

Max Activating Token Index: 12

Text #1

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0974. Min Act: -0.0001

Data Index: 1512778 (Python Code)

Max Activating Token Index: 1011

Text #2

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1516237 (Python Code)

Max Activating Token Index: 886

Text #3

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0924. Min Act: -0.0001

Data Index: 1633321 (Python Code)

Max Activating Token Index: 41

Text #4

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0954. Min Act: -0.0001

Data Index: 1556895 (Python Code)

Max Activating Token Index: 14

Text #5

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0916. Min Act: -0.0001

Data Index: 1415527 (Python Code)

Max Activating Token Index: 10

Text #6

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0908. Min Act: -0.0001

Data Index: 1551731 (Python Code)

Max Activating Token Index: 33

Text #7

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0906. Min Act: -0.0001

Data Index: 1426725 (Python Code)

Max Activating Token Index: 795

Text #8

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0896. Min Act: -0.0001

Data Index: 1414976 (Python Code)

Max Activating Token Index: 846

Text #9

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0891. Min Act: -0.0001

Data Index: 1442388 (Python Code)

Max Activating Token Index: 24

Text #10

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0905. Min Act: -0.0001

Data Index: 1521431 (Python Code)

Max Activating Token Index: 787

Text #11

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0875. Min Act: -0.0001

Data Index: 1417913 (Python Code)

Max Activating Token Index: 7

Text #12

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0905. Min Act: -0.0001

Data Index: 1372477 (Python Code)

Max Activating Token Index: 940

Text #13

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0868. Min Act: -0.0001

Data Index: 1467024 (Python Code)

Max Activating Token Index: 118

Text #14

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0869. Min Act: -0.0001

Data Index: 1436330 (Python Code)

Max Activating Token Index: 77

Text #15

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0860. Min Act: -0.0001

Data Index: 1638140 (Python Code)

Max Activating Token Index: 182

Text #16

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0860. Min Act: -0.0001

Data Index: 1601632 (Python Code)

Max Activating Token Index: 33

Text #17

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1485575 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0881. Min Act: -0.0001

Data Index: 1609262 (Python Code)

Max Activating Token Index: 61

Text #19

Max Range: 0.0987. Min Range: -0.0987

Max Act: 0.0865. Min Act: -0.0001

Data Index: 1436702 (Python Code)

Max Activating Token Index: 718