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

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

Neuron 3884 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.5614. Min Act: -0.0000

Data Index: 655628 (C4 (Web Text))

Max Activating Token Index: 58

Text #1

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.3481. Min Act: -0.0000

Data Index: 108223 (C4 (Web Text))

Max Activating Token Index: 980

Text #2

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.2989. Min Act: -0.0000

Data Index: 713554 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.3375. Min Act: -0.0000

Data Index: 729834 (C4 (Web Text))

Max Activating Token Index: 773

Text #4

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.1568. Min Act: -0.0000

Data Index: 1563288 (Python Code)

Max Activating Token Index: 259

Text #5

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.1757. Min Act: -0.0000

Data Index: 412267 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.1730. Min Act: -0.0000

Data Index: 625314 (C4 (Web Text))

Max Activating Token Index: 824

Text #7

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.1659. Min Act: -0.0000

Data Index: 1654653 (Python Code)

Max Activating Token Index: 781

Text #8

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.0868. Min Act: -0.0000

Data Index: 93814 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.1656. Min Act: -0.0000

Data Index: 1526052 (Python Code)

Max Activating Token Index: 671

Text #10

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.2264. Min Act: -0.0000

Data Index: 1592652 (Python Code)

Max Activating Token Index: 711

Text #11

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.1445. Min Act: -0.0000

Data Index: 1647195 (Python Code)

Max Activating Token Index: 370

Text #12

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.0839. Min Act: -0.0000

Data Index: 1617917 (Python Code)

Max Activating Token Index: 899

Text #13

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.1332. Min Act: -0.0000

Data Index: 15041 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.1532. Min Act: -0.0000

Data Index: 848969 (C4 (Web Text))

Max Activating Token Index: 541

Text #15

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.1977. Min Act: -0.0000

Data Index: 1443620 (Python Code)

Max Activating Token Index: 103

Text #16

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.1573. Min Act: -0.0000

Data Index: 948295 (C4 (Web Text))

Max Activating Token Index: 644

Text #17

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.1778. Min Act: -0.0000

Data Index: 1515983 (Python Code)

Max Activating Token Index: 107

Text #18

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.2489. Min Act: -0.0000

Data Index: 1381193 (Python Code)

Max Activating Token Index: 675

Text #19

Max Range: 1.5614. Min Range: -1.5614

Max Act: 1.1075. Min Act: -0.0000

Data Index: 1621363 (Python Code)

Max Activating Token Index: 578