Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 333 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2904. Min Act: -0.0003

Data Index: 1377640 (Python Code)

Max Activating Token Index: 420

Text #1

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2437. Min Act: -0.0003

Data Index: 1377519 (Python Code)

Max Activating Token Index: 168

Text #2

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2220. Min Act: -0.0003

Data Index: 1385575 (Python Code)

Max Activating Token Index: 1015

Text #3

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2060. Min Act: -0.0003

Data Index: 1375870 (Python Code)

Max Activating Token Index: 661

Text #4

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2027. Min Act: -0.0003

Data Index: 1486200 (Python Code)

Max Activating Token Index: 408

Text #5

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2007. Min Act: -0.0002

Data Index: 1647962 (Python Code)

Max Activating Token Index: 65

Text #6

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2038. Min Act: -0.0003

Data Index: 1424815 (Python Code)

Max Activating Token Index: 739

Text #7

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.2004. Min Act: -0.0002

Data Index: 1485240 (Python Code)

Max Activating Token Index: 420

Text #8

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.1993. Min Act: -0.0003

Data Index: 1494271 (Python Code)

Max Activating Token Index: 790

Text #9

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.1908. Min Act: -0.0003

Data Index: 1607366 (Python Code)

Max Activating Token Index: 226

Text #10

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.1782. Min Act: -0.0003

Data Index: 1637684 (Python Code)

Max Activating Token Index: 879

Text #11

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.1780. Min Act: -0.0003

Data Index: 1233219 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.1824. Min Act: -0.0003

Data Index: 1624946 (Python Code)

Max Activating Token Index: 190

Text #13

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.1738. Min Act: -0.0002

Data Index: 1615922 (Python Code)

Max Activating Token Index: 288

Text #14

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.1639. Min Act: -0.0003

Data Index: 660432 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.1682. Min Act: -0.0003

Data Index: 1630639 (Python Code)

Max Activating Token Index: 273

Text #16

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.1700. Min Act: -0.0002

Data Index: 1568091 (Python Code)

Max Activating Token Index: 23

Text #17

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.1701. Min Act: -0.0003

Data Index: 1469081 (Python Code)

Max Activating Token Index: 291

Text #18

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.1694. Min Act: -0.0002

Data Index: 1384302 (Python Code)

Max Activating Token Index: 125

Text #19

Max Range: 0.2904. Min Range: -0.2904

Max Act: 0.1679. Min Act: -0.0003

Data Index: 1514875 (Python Code)

Max Activating Token Index: 1016