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

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

Neuron 774 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4739. Min Range: -0.4739

Max Act: 0.4731. Min Act: -0.0000

Data Index: 508291 (C4 (Web Text))

Max Activating Token Index: 851

Text #1

Max Range: 0.4739. Min Range: -0.4739

Max Act: 0.4739. Min Act: -0.0000

Data Index: 992468 (C4 (Web Text))

Max Activating Token Index: 467

Text #2

Max Range: 0.4739. Min Range: -0.4739

Max Act: 0.4345. Min Act: -0.0000

Data Index: 414544 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 0.4739. Min Range: -0.4739

Max Act: 0.4513. Min Act: -0.0000

Data Index: 74571 (C4 (Web Text))

Max Activating Token Index: 334

Text #4

Max Range: 0.4739. Min Range: -0.4739

Max Act: 0.4727. Min Act: -0.0000

Data Index: 867041 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.4739. Min Range: -0.4739

Max Act: 0.4195. Min Act: -0.0000

Data Index: 430894 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 0.4739. Min Range: -0.4739

Max Act: 0.4175. Min Act: -0.0000

Data Index: 51477 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 0.4739. Min Range: -0.4739

Max Act: 0.3986. Min Act: -0.0000

Data Index: 506608 (C4 (Web Text))

Max Activating Token Index: 668

Text #8

Max Range: 0.4739. Min Range: -0.4739

Max Act: 0.4115. Min Act: -0.0000

Data Index: 1020633 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.4739. Min Range: -0.4739

Max Act: 0.3972. Min Act: -0.0000

Data Index: 417781 (C4 (Web Text))

Max Activating Token Index: 78

Text #10

Max Range: 0.4739. Min Range: -0.4739

Max Act: 0.3768. Min Act: -0.0000

Data Index: 1248433 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.4739. Min Range: -0.4739

Max Act: 0.3608. Min Act: -0.0000

Data Index: 779760 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 0.4739. Min Range: -0.4739

Max Act: 0.3568. Min Act: -0.0000

Data Index: 449892 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 0.4739. Min Range: -0.4739

Max Act: 0.3169. Min Act: -0.0000

Data Index: 1245541 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 0.4739. Min Range: -0.4739

Max Act: 0.3621. Min Act: -0.0000

Data Index: 302848 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.4739. Min Range: -0.4739

Max Act: 0.3497. Min Act: -0.0000

Data Index: 932937 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.4739. Min Range: -0.4739

Max Act: 0.3717. Min Act: -0.0000

Data Index: 728259 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 0.4739. Min Range: -0.4739

Max Act: 0.3559. Min Act: -0.0000

Data Index: 21031 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.4739. Min Range: -0.4739

Max Act: 0.3621. Min Act: -0.0000

Data Index: 1335738 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.4739. Min Range: -0.4739

Max Act: 0.3285. Min Act: -0.0000

Data Index: 1251310 (C4 (Web Text))

Max Activating Token Index: 606