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

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

Neuron 2896 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0006. Min Act: -0.0002

Data Index: 1087883 (C4 (Web Text))

Max Activating Token Index: 937

Text #1

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0006. Min Act: -0.0002

Data Index: 1608114 (Python Code)

Max Activating Token Index: 94

Text #2

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0006. Min Act: -0.0002

Data Index: 346196 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0002

Data Index: 1575787 (Python Code)

Max Activating Token Index: 124

Text #4

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0001

Data Index: 1551307 (Python Code)

Max Activating Token Index: 62

Text #5

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0002

Data Index: 1419197 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0002

Data Index: 728429 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0002

Data Index: 1621588 (Python Code)

Max Activating Token Index: 87

Text #8

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0001

Data Index: 1460862 (Python Code)

Max Activating Token Index: 55

Text #9

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0002

Data Index: 91553 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0002

Data Index: 1505796 (Python Code)

Max Activating Token Index: 117

Text #11

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0001

Data Index: 1634456 (Python Code)

Max Activating Token Index: 967

Text #12

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0002

Data Index: 1513927 (Python Code)

Max Activating Token Index: 74

Text #13

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0002

Data Index: 1069666 (C4 (Web Text))

Max Activating Token Index: 874

Text #14

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0002

Data Index: 1423467 (Python Code)

Max Activating Token Index: 97

Text #15

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0002

Data Index: 141480 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0002

Data Index: 318963 (C4 (Web Text))

Max Activating Token Index: 982

Text #17

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0002

Data Index: 1535783 (Python Code)

Max Activating Token Index: 134

Text #18

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0001

Data Index: 1549963 (Python Code)

Max Activating Token Index: 70

Text #19

Max Range: 0.0006. Min Range: -0.0006

Max Act: 0.0005. Min Act: -0.0001

Data Index: 1498079 (Python Code)

Max Activating Token Index: 79