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

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

Neuron 1007 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2192. Min Range: -1.2192

Max Act: 1.2192. Min Act: -0.0000

Data Index: 1573725 (Python Code)

Max Activating Token Index: 675

Text #1

Max Range: 1.2192. Min Range: -1.2192

Max Act: 1.0530. Min Act: -0.0000

Data Index: 1060235 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 1.2192. Min Range: -1.2192

Max Act: 0.9981. Min Act: -0.0000

Data Index: 1486512 (Python Code)

Max Activating Token Index: 636

Text #3

Max Range: 1.2192. Min Range: -1.2192

Max Act: 1.0887. Min Act: -0.0000

Data Index: 1542808 (Python Code)

Max Activating Token Index: 397

Text #4

Max Range: 1.2192. Min Range: -1.2192

Max Act: 0.9547. Min Act: -0.0000

Data Index: 1515438 (Python Code)

Max Activating Token Index: 725

Text #5

Max Range: 1.2192. Min Range: -1.2192

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1631186 (Python Code)

Max Activating Token Index: 348

Text #6

Max Range: 1.2192. Min Range: -1.2192

Max Act: 0.8726. Min Act: -0.0000

Data Index: 1581295 (Python Code)

Max Activating Token Index: 442

Text #7

Max Range: 1.2192. Min Range: -1.2192

Max Act: 0.8946. Min Act: -0.0000

Data Index: 121686 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 1.2192. Min Range: -1.2192

Max Act: 0.8723. Min Act: -0.0000

Data Index: 1539517 (Python Code)

Max Activating Token Index: 109

Text #9

Max Range: 1.2192. Min Range: -1.2192

Max Act: 0.8592. Min Act: -0.0000

Data Index: 689580 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 1.2192. Min Range: -1.2192

Max Act: 0.8728. Min Act: -0.0000

Data Index: 1581395 (Python Code)

Max Activating Token Index: 681

Text #11

Max Range: 1.2192. Min Range: -1.2192

Max Act: 0.8735. Min Act: -0.0000

Data Index: 1521391 (Python Code)

Max Activating Token Index: 600

Text #12

Max Range: 1.2192. Min Range: -1.2192

Max Act: 0.8458. Min Act: 0.0001

Data Index: 334440 (C4 (Web Text))

Max Activating Token Index: 81

Text #13

Max Range: 1.2192. Min Range: -1.2192

Max Act: 0.8973. Min Act: -0.0000

Data Index: 15407 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 1.2192. Min Range: -1.2192

Max Act: 0.8143. Min Act: -0.0000

Data Index: 1594412 (Python Code)

Max Activating Token Index: 769

Text #15

Max Range: 1.2192. Min Range: -1.2192

Max Act: 0.8222. Min Act: -0.0000

Data Index: 1509626 (Python Code)

Max Activating Token Index: 409

Text #16

Max Range: 1.2192. Min Range: -1.2192

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1315697 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 1.2192. Min Range: -1.2192

Max Act: 0.8180. Min Act: -0.0000

Data Index: 1467940 (Python Code)

Max Activating Token Index: 702

Text #18

Max Range: 1.2192. Min Range: -1.2192

Max Act: 0.8308. Min Act: -0.0000

Data Index: 27179 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 1.2192. Min Range: -1.2192

Max Act: 0.8117. Min Act: -0.0000

Data Index: 1370326 (Python Code)

Max Activating Token Index: 703