Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 561 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.2097. Min Act: -0.0000

Data Index: 276638 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1899. Min Act: -0.0001

Data Index: 908679 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1891. Min Act: -0.0000

Data Index: 860798 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1738. Min Act: -0.0000

Data Index: 1038050 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1800. Min Act: -0.0001

Data Index: 133291 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1905. Min Act: -0.0000

Data Index: 278957 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1765. Min Act: -0.0000

Data Index: 249851 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1689. Min Act: -0.0000

Data Index: 361435 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1671. Min Act: -0.0000

Data Index: 290237 (C4 (Web Text))

Max Activating Token Index: 96

Text #9

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1673. Min Act: -0.0000

Data Index: 1106091 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1654. Min Act: -0.0000

Data Index: 567532 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1603. Min Act: -0.0000

Data Index: 1182235 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1707. Min Act: -0.0000

Data Index: 755228 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1576. Min Act: -0.0000

Data Index: 891563 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1643. Min Act: -0.0000

Data Index: 234920 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1688. Min Act: -0.0001

Data Index: 971378 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1286479 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1591. Min Act: -0.0001

Data Index: 130865 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1597. Min Act: -0.0001

Data Index: 282266 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.2097. Min Range: -0.2097

Max Act: 0.1519. Min Act: -0.0000

Data Index: 757597 (C4 (Web Text))

Max Activating Token Index: 197