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

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

Neuron 1639 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.1891. Min Act: -0.0001

Data Index: 1438345 (Python Code)

Max Activating Token Index: 622

Text #1

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.1021. Min Act: -0.0001

Data Index: 1475787 (Python Code)

Max Activating Token Index: 163

Text #2

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.1998. Min Act: -0.0001

Data Index: 1576188 (Python Code)

Max Activating Token Index: 303

Text #3

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.0242. Min Act: -0.0001

Data Index: 1496192 (Python Code)

Max Activating Token Index: 53

Text #4

Max Range: 3.1998. Min Range: -3.1998

Max Act: 3.0086. Min Act: -0.0001

Data Index: 576521 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 3.1998. Min Range: -3.1998

Max Act: 2.6753. Min Act: -0.0001

Data Index: 1467350 (Python Code)

Max Activating Token Index: 680

Text #6

Max Range: 3.1998. Min Range: -3.1998

Max Act: 2.9539. Min Act: -0.0001

Data Index: 1608332 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 3.1998. Min Range: -3.1998

Max Act: 2.9081. Min Act: -0.0001

Data Index: 1615413 (Python Code)

Max Activating Token Index: 86

Text #8

Max Range: 3.1998. Min Range: -3.1998

Max Act: 2.7438. Min Act: -0.0001

Data Index: 1558638 (Python Code)

Max Activating Token Index: 891

Text #9

Max Range: 3.1998. Min Range: -3.1998

Max Act: 2.7074. Min Act: -0.0001

Data Index: 1635712 (Python Code)

Max Activating Token Index: 144

Text #10

Max Range: 3.1998. Min Range: -3.1998

Max Act: 2.8343. Min Act: -0.0001

Data Index: 1471237 (Python Code)

Max Activating Token Index: 877

Text #11

Max Range: 3.1998. Min Range: -3.1998

Max Act: 2.6754. Min Act: -0.0001

Data Index: 1460020 (Python Code)

Max Activating Token Index: 930

Text #12

Max Range: 3.1998. Min Range: -3.1998

Max Act: 2.6716. Min Act: -0.0001

Data Index: 1595839 (Python Code)

Max Activating Token Index: 412

Text #13

Max Range: 3.1998. Min Range: -3.1998

Max Act: 2.8096. Min Act: -0.0001

Data Index: 179105 (C4 (Web Text))

Max Activating Token Index: 839

Text #14

Max Range: 3.1998. Min Range: -3.1998

Max Act: 2.6182. Min Act: -0.0001

Data Index: 1569991 (Python Code)

Max Activating Token Index: 5

Text #15

Max Range: 3.1998. Min Range: -3.1998

Max Act: 2.5661. Min Act: -0.0001

Data Index: 1643264 (Python Code)

Max Activating Token Index: 176

Text #16

Max Range: 3.1998. Min Range: -3.1998

Max Act: 2.6965. Min Act: -0.0001

Data Index: 1522085 (Python Code)

Max Activating Token Index: 724

Text #17

Max Range: 3.1998. Min Range: -3.1998

Max Act: 2.3963. Min Act: -0.0001

Data Index: 1369957 (Python Code)

Max Activating Token Index: 74

Text #18

Max Range: 3.1998. Min Range: -3.1998

Max Act: 2.7813. Min Act: -0.0001

Data Index: 1607209 (Python Code)

Max Activating Token Index: 95

Text #19

Max Range: 3.1998. Min Range: -3.1998

Max Act: 2.4781. Min Act: -0.0001

Data Index: 1654062 (Python Code)

Max Activating Token Index: 71