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

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

Neuron 3285 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2128. Min Range: -1.2128

Max Act: 1.2128. Min Act: -0.0000

Data Index: 986154 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 1.2128. Min Range: -1.2128

Max Act: 1.2128. Min Act: -0.0001

Data Index: 1570313 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 1.2128. Min Range: -1.2128

Max Act: 1.2128. Min Act: -0.0000

Data Index: 285171 (C4 (Web Text))

Max Activating Token Index: 1

Text #3

Max Range: 1.2128. Min Range: -1.2128

Max Act: 1.2128. Min Act: -0.0000

Data Index: 183800 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 1.2128. Min Range: -1.2128

Max Act: 1.2128. Min Act: -0.0000

Data Index: 20765 (C4 (Web Text))

Max Activating Token Index: 1

Text #5

Max Range: 1.2128. Min Range: -1.2128

Max Act: 1.2128. Min Act: -0.0000

Data Index: 718923 (C4 (Web Text))

Max Activating Token Index: 1

Text #6

Max Range: 1.2128. Min Range: -1.2128

Max Act: 1.2128. Min Act: -0.0000

Data Index: 1297554 (C4 (Web Text))

Max Activating Token Index: 1

Text #7

Max Range: 1.2128. Min Range: -1.2128

Max Act: 1.2128. Min Act: -0.0001

Data Index: 1169777 (C4 (Web Text))

Max Activating Token Index: 1

Text #8

Max Range: 1.2128. Min Range: -1.2128

Max Act: 1.2128. Min Act: -0.0000

Data Index: 100048 (C4 (Web Text))

Max Activating Token Index: 1

Text #9

Max Range: 1.2128. Min Range: -1.2128

Max Act: 1.2128. Min Act: -0.0000

Data Index: 845213 (C4 (Web Text))

Max Activating Token Index: 1

Text #10

Max Range: 1.2128. Min Range: -1.2128

Max Act: 1.0669. Min Act: -0.0001

Data Index: 1616118 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 1.2128. Min Range: -1.2128

Max Act: 1.0669. Min Act: -0.0000

Data Index: 1655661 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 1.2128. Min Range: -1.2128

Max Act: 1.0669. Min Act: -0.0001

Data Index: 1514463 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 1.2128. Min Range: -1.2128

Max Act: 1.0669. Min Act: -0.0001

Data Index: 1484147 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 1.2128. Min Range: -1.2128

Max Act: 1.0669. Min Act: -0.0000

Data Index: 1568931 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 1.2128. Min Range: -1.2128

Max Act: 1.0669. Min Act: -0.0001

Data Index: 1473645 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 1.2128. Min Range: -1.2128

Max Act: 1.0669. Min Act: -0.0000

Data Index: 1382766 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 1.2128. Min Range: -1.2128

Max Act: 1.0669. Min Act: -0.0001

Data Index: 1630334 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 1.2128. Min Range: -1.2128

Max Act: 1.0669. Min Act: -0.0000

Data Index: 82007 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 1.2128. Min Range: -1.2128

Max Act: 1.0669. Min Act: -0.0000

Data Index: 281371 (C4 (Web Text))

Max Activating Token Index: 1