Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 46 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0841. Min Act: -0.0002

Data Index: 1477970 (Python Code)

Max Activating Token Index: 994

Text #1

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1652627 (Python Code)

Max Activating Token Index: 350

Text #2

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0924. Min Act: -0.0002

Data Index: 1655942 (Python Code)

Max Activating Token Index: 931

Text #3

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0847. Min Act: -0.0002

Data Index: 1411612 (Python Code)

Max Activating Token Index: 849

Text #4

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0875. Min Act: -0.0002

Data Index: 1423848 (Python Code)

Max Activating Token Index: 970

Text #5

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0815. Min Act: -0.0002

Data Index: 1409542 (Python Code)

Max Activating Token Index: 451

Text #6

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0878. Min Act: -0.0002

Data Index: 1492222 (Python Code)

Max Activating Token Index: 754

Text #7

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1596625 (Python Code)

Max Activating Token Index: 759

Text #8

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0816. Min Act: -0.0002

Data Index: 1634632 (Python Code)

Max Activating Token Index: 713

Text #9

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1593312 (Python Code)

Max Activating Token Index: 125

Text #10

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0844. Min Act: -0.0002

Data Index: 1620118 (Python Code)

Max Activating Token Index: 799

Text #11

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1465673 (Python Code)

Max Activating Token Index: 431

Text #12

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0797. Min Act: -0.0002

Data Index: 1486749 (Python Code)

Max Activating Token Index: 303

Text #13

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0776. Min Act: -0.0002

Data Index: 1480581 (Python Code)

Max Activating Token Index: 220

Text #14

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0799. Min Act: -0.0002

Data Index: 1375679 (Python Code)

Max Activating Token Index: 123

Text #15

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0828. Min Act: -0.0002

Data Index: 1361667 (Python Code)

Max Activating Token Index: 208

Text #16

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1581345 (Python Code)

Max Activating Token Index: 298

Text #17

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0842. Min Act: -0.0002

Data Index: 1576934 (Python Code)

Max Activating Token Index: 537

Text #18

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0795. Min Act: -0.0002

Data Index: 1449636 (Python Code)

Max Activating Token Index: 638

Text #19

Max Range: 0.0924. Min Range: -0.0924

Max Act: 0.0754. Min Act: -0.0002

Data Index: 1637858 (Python Code)

Max Activating Token Index: 793