Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2349 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.2338. Min Act: -0.0000

Data Index: 329937 (C4 (Web Text))

Max Activating Token Index: 720

Text #1

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.2345. Min Act: -0.0000

Data Index: 195460 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.2249. Min Act: -0.0000

Data Index: 335578 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.2242. Min Act: -0.0000

Data Index: 547082 (C4 (Web Text))

Max Activating Token Index: 67

Text #4

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1015513 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1350292 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.2235. Min Act: -0.0000

Data Index: 596926 (C4 (Web Text))

Max Activating Token Index: 856

Text #7

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.2068. Min Act: -0.0000

Data Index: 138311 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1980. Min Act: -0.0000

Data Index: 76147 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1995. Min Act: -0.0000

Data Index: 37704 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.2126. Min Act: -0.0000

Data Index: 248750 (C4 (Web Text))

Max Activating Token Index: 1001

Text #11

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1859. Min Act: -0.0000

Data Index: 300009 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1959. Min Act: -0.0000

Data Index: 696904 (C4 (Web Text))

Max Activating Token Index: 421

Text #13

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1923. Min Act: -0.0000

Data Index: 215594 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1916. Min Act: -0.0000

Data Index: 16045 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1865. Min Act: -0.0000

Data Index: 1059445 (C4 (Web Text))

Max Activating Token Index: 606

Text #16

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1795. Min Act: -0.0000

Data Index: 761656 (C4 (Web Text))

Max Activating Token Index: 17

Text #17

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1942. Min Act: -0.0000

Data Index: 429224 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1949. Min Act: -0.0001

Data Index: 1077820 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 0.2345. Min Range: -0.2345

Max Act: 0.1915. Min Act: -0.0000

Data Index: 545365 (C4 (Web Text))

Max Activating Token Index: 785