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

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

Neuron 3013 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: 0.2860. Min Range: -0.2860

Max Act: 0.2860. Min Act: -0.0000

Data Index: 1464393 (Python Code)

Max Activating Token Index: 328

Text #1

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2530. Min Act: -0.0000

Data Index: 583023 (C4 (Web Text))

Max Activating Token Index: 440

Text #2

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2453. Min Act: -0.0000

Data Index: 1549762 (Python Code)

Max Activating Token Index: 819

Text #3

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2275. Min Act: -0.0000

Data Index: 1405422 (Python Code)

Max Activating Token Index: 133

Text #4

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1488511 (Python Code)

Max Activating Token Index: 737

Text #5

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2242. Min Act: -0.0000

Data Index: 1298858 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2289. Min Act: -0.0000

Data Index: 1588945 (Python Code)

Max Activating Token Index: 107

Text #7

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1507575 (Python Code)

Max Activating Token Index: 870

Text #8

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2322. Min Act: -0.0000

Data Index: 1595277 (Python Code)

Max Activating Token Index: 705

Text #9

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1372849 (Python Code)

Max Activating Token Index: 613

Text #10

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1533730 (Python Code)

Max Activating Token Index: 589

Text #11

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2284. Min Act: -0.0000

Data Index: 1641605 (Python Code)

Max Activating Token Index: 803

Text #12

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2147. Min Act: -0.0000

Data Index: 1614739 (Python Code)

Max Activating Token Index: 623

Text #13

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2256. Min Act: -0.0000

Data Index: 1532370 (Python Code)

Max Activating Token Index: 524

Text #14

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2143. Min Act: -0.0000

Data Index: 1464051 (Python Code)

Max Activating Token Index: 41

Text #15

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2181. Min Act: -0.0000

Data Index: 1540364 (Python Code)

Max Activating Token Index: 951

Text #16

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.1912. Min Act: -0.0000

Data Index: 593842 (C4 (Web Text))

Max Activating Token Index: 805

Text #17

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2057. Min Act: -0.0000

Data Index: 1492806 (Python Code)

Max Activating Token Index: 33

Text #18

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2039. Min Act: -0.0000

Data Index: 1430539 (Python Code)

Max Activating Token Index: 594

Text #19

Max Range: 0.2860. Min Range: -0.2860

Max Act: 0.2011. Min Act: -0.0000

Data Index: 1448077 (Python Code)

Max Activating Token Index: 54