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

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

Neuron 2064 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1141. Min Act: -0.0002

Data Index: 1558788 (Python Code)

Max Activating Token Index: 882

Text #1

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1095. Min Act: -0.0002

Data Index: 1613000 (Python Code)

Max Activating Token Index: 3

Text #2

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1135. Min Act: -0.0002

Data Index: 1521276 (Python Code)

Max Activating Token Index: 877

Text #3

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0899. Min Act: -0.0002

Data Index: 1607469 (Python Code)

Max Activating Token Index: 609

Text #4

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1033. Min Act: -0.0002

Data Index: 1392999 (Python Code)

Max Activating Token Index: 386

Text #5

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0952. Min Act: -0.0002

Data Index: 1430178 (Python Code)

Max Activating Token Index: 925

Text #6

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1041. Min Act: -0.0002

Data Index: 1620952 (Python Code)

Max Activating Token Index: 178

Text #7

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0996. Min Act: -0.0002

Data Index: 1462062 (Python Code)

Max Activating Token Index: 844

Text #8

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1029. Min Act: -0.0002

Data Index: 1623654 (Python Code)

Max Activating Token Index: 679

Text #9

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1001. Min Act: -0.0002

Data Index: 1490185 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0866. Min Act: -0.0002

Data Index: 1623862 (Python Code)

Max Activating Token Index: 664

Text #11

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0964. Min Act: -0.0002

Data Index: 1396276 (Python Code)

Max Activating Token Index: 985

Text #12

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1411205 (Python Code)

Max Activating Token Index: 649

Text #13

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0982. Min Act: -0.0002

Data Index: 1435763 (Python Code)

Max Activating Token Index: 5

Text #14

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0927. Min Act: -0.0002

Data Index: 1567577 (Python Code)

Max Activating Token Index: 986

Text #15

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0904. Min Act: -0.0002

Data Index: 1565114 (Python Code)

Max Activating Token Index: 957

Text #16

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0930. Min Act: -0.0002

Data Index: 1631498 (Python Code)

Max Activating Token Index: 476

Text #17

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0883. Min Act: -0.0002

Data Index: 1435743 (Python Code)

Max Activating Token Index: 851

Text #18

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0926. Min Act: -0.0002

Data Index: 1534334 (Python Code)

Max Activating Token Index: 4

Text #19

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0962. Min Act: -0.0002

Data Index: 1546386 (Python Code)

Max Activating Token Index: 272