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

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

Neuron 2060 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2530. Min Act: -0.0002

Data Index: 1402462 (Python Code)

Max Activating Token Index: 386

Text #1

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2094. Min Act: -0.0002

Data Index: 1590029 (Python Code)

Max Activating Token Index: 333

Text #2

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1880. Min Act: -0.0002

Data Index: 1580401 (Python Code)

Max Activating Token Index: 244

Text #3

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1998. Min Act: -0.0002

Data Index: 1480099 (Python Code)

Max Activating Token Index: 824

Text #4

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2212. Min Act: -0.0002

Data Index: 1532815 (Python Code)

Max Activating Token Index: 730

Text #5

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1995. Min Act: -0.0002

Data Index: 1436197 (Python Code)

Max Activating Token Index: 14

Text #6

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1986. Min Act: -0.0002

Data Index: 1596658 (Python Code)

Max Activating Token Index: 765

Text #7

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2019. Min Act: -0.0002

Data Index: 1544224 (Python Code)

Max Activating Token Index: 458

Text #8

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1956. Min Act: -0.0002

Data Index: 1387792 (Python Code)

Max Activating Token Index: 34

Text #9

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1844. Min Act: -0.0002

Data Index: 1369683 (Python Code)

Max Activating Token Index: 204

Text #10

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1993. Min Act: -0.0002

Data Index: 1510070 (Python Code)

Max Activating Token Index: 228

Text #11

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1894. Min Act: -0.0002

Data Index: 1550920 (Python Code)

Max Activating Token Index: 169

Text #12

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1800. Min Act: -0.0002

Data Index: 1647850 (Python Code)

Max Activating Token Index: 14

Text #13

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1848. Min Act: -0.0002

Data Index: 1605665 (Python Code)

Max Activating Token Index: 191

Text #14

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1849. Min Act: -0.0002

Data Index: 1480387 (Python Code)

Max Activating Token Index: 503

Text #15

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1768. Min Act: -0.0002

Data Index: 1418759 (Python Code)

Max Activating Token Index: 133

Text #16

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.2046. Min Act: -0.0002

Data Index: 1501993 (Python Code)

Max Activating Token Index: 900

Text #17

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1701. Min Act: -0.0002

Data Index: 1641026 (Python Code)

Max Activating Token Index: 301

Text #18

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1715. Min Act: -0.0002

Data Index: 1421259 (Python Code)

Max Activating Token Index: 73

Text #19

Max Range: 0.2530. Min Range: -0.2530

Max Act: 0.1716. Min Act: -0.0002

Data Index: 1647976 (Python Code)

Max Activating Token Index: 33