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

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

Neuron 1368 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1524. Min Act: -0.0001

Data Index: 1536113 (Python Code)

Max Activating Token Index: 387

Text #1

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1621135 (Python Code)

Max Activating Token Index: 176

Text #2

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1003. Min Act: -0.0001

Data Index: 1656980 (Python Code)

Max Activating Token Index: 161

Text #3

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0991. Min Act: -0.0001

Data Index: 1592074 (Python Code)

Max Activating Token Index: 633

Text #4

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0949. Min Act: -0.0001

Data Index: 1654022 (Python Code)

Max Activating Token Index: 351

Text #5

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0926. Min Act: -0.0001

Data Index: 1480279 (Python Code)

Max Activating Token Index: 162

Text #6

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0987. Min Act: -0.0001

Data Index: 1449778 (Python Code)

Max Activating Token Index: 268

Text #7

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1093. Min Act: -0.0001

Data Index: 1630533 (Python Code)

Max Activating Token Index: 195

Text #8

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0971. Min Act: -0.0001

Data Index: 1558708 (Python Code)

Max Activating Token Index: 147

Text #9

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0954. Min Act: -0.0001

Data Index: 1473563 (Python Code)

Max Activating Token Index: 179

Text #10

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0931. Min Act: -0.0001

Data Index: 1650703 (Python Code)

Max Activating Token Index: 484

Text #11

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0929. Min Act: -0.0001

Data Index: 1614196 (Python Code)

Max Activating Token Index: 179

Text #12

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0894. Min Act: -0.0001

Data Index: 1520248 (Python Code)

Max Activating Token Index: 597

Text #13

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0931. Min Act: -0.0001

Data Index: 1590829 (Python Code)

Max Activating Token Index: 392

Text #14

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0813. Min Act: -0.0001

Data Index: 1444164 (Python Code)

Max Activating Token Index: 709

Text #15

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0869. Min Act: -0.0001

Data Index: 1623301 (Python Code)

Max Activating Token Index: 568

Text #16

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1535685 (Python Code)

Max Activating Token Index: 354

Text #17

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0937. Min Act: -0.0001

Data Index: 1611565 (Python Code)

Max Activating Token Index: 520

Text #18

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0844. Min Act: -0.0001

Data Index: 1513455 (Python Code)

Max Activating Token Index: 923

Text #19

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1539377 (Python Code)

Max Activating Token Index: 979