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

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

Neuron 1966 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.2309. Min Act: -0.0000

Data Index: 1212527 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.2152. Min Act: -0.0000

Data Index: 875479 (C4 (Web Text))

Max Activating Token Index: 458

Text #2

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1850. Min Act: -0.0000

Data Index: 993927 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1711. Min Act: -0.0000

Data Index: 910988 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1864. Min Act: -0.0000

Data Index: 96777 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1851. Min Act: -0.0000

Data Index: 665967 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1724. Min Act: -0.0000

Data Index: 1324428 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1713. Min Act: -0.0000

Data Index: 922930 (C4 (Web Text))

Max Activating Token Index: 115

Text #8

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1616. Min Act: -0.0000

Data Index: 1353008 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1588. Min Act: -0.0000

Data Index: 371880 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1793. Min Act: -0.0000

Data Index: 1004112 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1677. Min Act: -0.0000

Data Index: 942408 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1663. Min Act: -0.0000

Data Index: 795619 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1532. Min Act: -0.0000

Data Index: 1242758 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1635. Min Act: -0.0000

Data Index: 60256 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1687. Min Act: -0.0000

Data Index: 1128508 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1507. Min Act: -0.0000

Data Index: 1001553 (C4 (Web Text))

Max Activating Token Index: 1014

Text #17

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1497. Min Act: -0.0000

Data Index: 708332 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1486. Min Act: -0.0000

Data Index: 499801 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 0.2309. Min Range: -0.2309

Max Act: 0.1472. Min Act: -0.0000

Data Index: 343892 (C4 (Web Text))

Max Activating Token Index: 833