Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 314 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.9945. Min Act: -0.0004

Data Index: 1581396 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.8233. Min Act: -0.0003

Data Index: 1585656 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.7821. Min Act: -0.0003

Data Index: 1402853 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.7404. Min Act: -0.0003

Data Index: 1646836 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.7620. Min Act: -0.0003

Data Index: 1586958 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.6489. Min Act: -0.0003

Data Index: 1524797 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.6533. Min Act: -0.0003

Data Index: 1400871 (Python Code)

Max Activating Token Index: 577

Text #7

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.6118. Min Act: -0.0003

Data Index: 1635311 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.5653. Min Act: -0.0003

Data Index: 1475933 (Python Code)

Max Activating Token Index: 358

Text #9

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.6222. Min Act: -0.0003

Data Index: 1528698 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.6152. Min Act: -0.0003

Data Index: 1629846 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.5643. Min Act: -0.0004

Data Index: 1653016 (Python Code)

Max Activating Token Index: 1023

Text #12

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.5612. Min Act: -0.0003

Data Index: 1427519 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.5957. Min Act: -0.0003

Data Index: 1483017 (Python Code)

Max Activating Token Index: 1023

Text #14

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.6165. Min Act: -0.0003

Data Index: 1656322 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.5762. Min Act: -0.0003

Data Index: 1598356 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.5952. Min Act: -0.0003

Data Index: 1503757 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.5673. Min Act: -0.0003

Data Index: 1637432 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.5685. Min Act: -0.0003

Data Index: 1542543 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 0.9945. Min Range: -0.9945

Max Act: 0.5787. Min Act: -0.0003

Data Index: 1564045 (Python Code)

Max Activating Token Index: 1023