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

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

Neuron 4172 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2811. Min Act: -0.0000

Data Index: 1524261 (Python Code)

Max Activating Token Index: 166

Text #1

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2261. Min Act: -0.0000

Data Index: 1543150 (Python Code)

Max Activating Token Index: 430

Text #2

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.2041. Min Act: -0.0000

Data Index: 1432143 (Python Code)

Max Activating Token Index: 1021

Text #3

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1747. Min Act: -0.0000

Data Index: 1624946 (Python Code)

Max Activating Token Index: 667

Text #4

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1742. Min Act: -0.0000

Data Index: 1591699 (Python Code)

Max Activating Token Index: 1019

Text #5

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1771. Min Act: 0.0001

Data Index: 1537595 (Python Code)

Max Activating Token Index: 434

Text #6

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1778. Min Act: -0.0000

Data Index: 1637033 (Python Code)

Max Activating Token Index: 232

Text #7

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1656. Min Act: 0.0000

Data Index: 1458800 (Python Code)

Max Activating Token Index: 335

Text #8

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1405840 (Python Code)

Max Activating Token Index: 811

Text #9

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1388537 (Python Code)

Max Activating Token Index: 885

Text #10

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1809. Min Act: -0.0000

Data Index: 1365283 (Python Code)

Max Activating Token Index: 160

Text #11

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1739. Min Act: -0.0000

Data Index: 1458515 (Python Code)

Max Activating Token Index: 189

Text #12

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1634. Min Act: -0.0000

Data Index: 1518233 (Python Code)

Max Activating Token Index: 684

Text #13

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1671. Min Act: -0.0000

Data Index: 1459279 (Python Code)

Max Activating Token Index: 182

Text #14

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1522. Min Act: 0.0000

Data Index: 1379697 (Python Code)

Max Activating Token Index: 941

Text #15

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1768. Min Act: -0.0000

Data Index: 1407575 (Python Code)

Max Activating Token Index: 391

Text #16

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1622. Min Act: -0.0000

Data Index: 1467436 (Python Code)

Max Activating Token Index: 70

Text #17

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1609817 (Python Code)

Max Activating Token Index: 219

Text #18

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1655. Min Act: -0.0000

Data Index: 1594974 (Python Code)

Max Activating Token Index: 558

Text #19

Max Range: 0.2811. Min Range: -0.2811

Max Act: 0.1671. Min Act: -0.0000

Data Index: 1611120 (Python Code)

Max Activating Token Index: 432