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

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

Neuron 1637 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: 0.0090. Min Range: -0.0090

Max Act: 0.0090. Min Act: -0.0002

Data Index: 1528008 (Python Code)

Max Activating Token Index: 313

Text #1

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1461238 (Python Code)

Max Activating Token Index: 150

Text #2

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0088. Min Act: -0.0001

Data Index: 1609524 (Python Code)

Max Activating Token Index: 125

Text #3

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1458398 (Python Code)

Max Activating Token Index: 259

Text #4

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1337257 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0088. Min Act: -0.0002

Data Index: 1655817 (Python Code)

Max Activating Token Index: 310

Text #6

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1603331 (Python Code)

Max Activating Token Index: 626

Text #7

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1470029 (Python Code)

Max Activating Token Index: 109

Text #8

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1539986 (Python Code)

Max Activating Token Index: 376

Text #9

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0085. Min Act: -0.0002

Data Index: 1599266 (Python Code)

Max Activating Token Index: 404

Text #10

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0086. Min Act: -0.0002

Data Index: 1613426 (Python Code)

Max Activating Token Index: 40

Text #11

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0086. Min Act: -0.0002

Data Index: 1623139 (Python Code)

Max Activating Token Index: 67

Text #12

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0086. Min Act: -0.0002

Data Index: 1575793 (Python Code)

Max Activating Token Index: 100

Text #13

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0085. Min Act: -0.0002

Data Index: 1439635 (Python Code)

Max Activating Token Index: 72

Text #14

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0086. Min Act: -0.0002

Data Index: 1595374 (Python Code)

Max Activating Token Index: 73

Text #15

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0085. Min Act: -0.0002

Data Index: 1572143 (Python Code)

Max Activating Token Index: 271

Text #16

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1455154 (Python Code)

Max Activating Token Index: 131

Text #17

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0085. Min Act: -0.0002

Data Index: 1448875 (Python Code)

Max Activating Token Index: 164

Text #18

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1569107 (Python Code)

Max Activating Token Index: 274

Text #19

Max Range: 0.0090. Min Range: -0.0090

Max Act: 0.0083. Min Act: -0.0002

Data Index: 1375872 (Python Code)

Max Activating Token Index: 585