Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5253 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.2210. Min Act: -0.0000

Data Index: 1421090 (Python Code)

Max Activating Token Index: 777

Text #1

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.2283. Min Act: -0.0000

Data Index: 1533147 (Python Code)

Max Activating Token Index: 880

Text #2

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.2108. Min Act: -0.0000

Data Index: 763109 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1833. Min Act: -0.0000

Data Index: 1399405 (Python Code)

Max Activating Token Index: 396

Text #4

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1710. Min Act: -0.0000

Data Index: 904039 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1657. Min Act: -0.0000

Data Index: 1404646 (Python Code)

Max Activating Token Index: 866

Text #6

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1725. Min Act: -0.0000

Data Index: 838213 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1714. Min Act: -0.0000

Data Index: 1641291 (Python Code)

Max Activating Token Index: 666

Text #8

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1685. Min Act: -0.0000

Data Index: 1003175 (C4 (Web Text))

Max Activating Token Index: 768

Text #9

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1616. Min Act: -0.0000

Data Index: 754860 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1625. Min Act: -0.0000

Data Index: 1345871 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1576. Min Act: -0.0000

Data Index: 1400645 (Python Code)

Max Activating Token Index: 840

Text #12

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1575. Min Act: -0.0000

Data Index: 1590668 (Python Code)

Max Activating Token Index: 238

Text #13

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1530. Min Act: -0.0000

Data Index: 64986 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1516. Min Act: -0.0000

Data Index: 635557 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1371. Min Act: -0.0000

Data Index: 1083921 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1570. Min Act: -0.0000

Data Index: 1417829 (Python Code)

Max Activating Token Index: 707

Text #17

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1545. Min Act: -0.0000

Data Index: 301149 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1586. Min Act: -0.0000

Data Index: 1307751 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.2283. Min Range: -0.2283

Max Act: 0.1514. Min Act: -0.0000

Data Index: 1269207 (C4 (Web Text))

Max Activating Token Index: 827