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

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

Neuron 275 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: 0.1739. Min Range: -0.1739

Max Act: 0.1738. Min Act: -0.0000

Data Index: 205772 (C4 (Web Text))

Max Activating Token Index: 279

Text #1

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1706. Min Act: -0.0000

Data Index: 470241 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1520. Min Act: -0.0000

Data Index: 506218 (C4 (Web Text))

Max Activating Token Index: 805

Text #3

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1739. Min Act: -0.0000

Data Index: 23484 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1675. Min Act: -0.0000

Data Index: 1116118 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1629. Min Act: -0.0000

Data Index: 1032475 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1634. Min Act: -0.0000

Data Index: 963811 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1658. Min Act: -0.0000

Data Index: 1277817 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1641. Min Act: -0.0000

Data Index: 906352 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1633. Min Act: -0.0000

Data Index: 580800 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1645. Min Act: -0.0000

Data Index: 1157531 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1624. Min Act: -0.0000

Data Index: 1201301 (C4 (Web Text))

Max Activating Token Index: 341

Text #12

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1629. Min Act: -0.0000

Data Index: 615899 (C4 (Web Text))

Max Activating Token Index: 750

Text #13

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1558. Min Act: -0.0000

Data Index: 1652439 (Python Code)

Max Activating Token Index: 81

Text #14

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1606. Min Act: -0.0000

Data Index: 24382 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1598. Min Act: -0.0000

Data Index: 198635 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1553. Min Act: -0.0000

Data Index: 150731 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1638. Min Act: -0.0000

Data Index: 1233444 (C4 (Web Text))

Max Activating Token Index: 262

Text #18

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1668. Min Act: -0.0000

Data Index: 913727 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.1739. Min Range: -0.1739

Max Act: 0.1587. Min Act: -0.0000

Data Index: 131237 (C4 (Web Text))

Max Activating Token Index: 207