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

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

Neuron 3020 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.3774. Min Act: -0.0000

Data Index: 482804 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2475. Min Act: -0.0000

Data Index: 1510432 (Python Code)

Max Activating Token Index: 450

Text #2

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2272. Min Act: -0.0000

Data Index: 194857 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2265. Min Act: -0.0000

Data Index: 1220621 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2163. Min Act: -0.0000

Data Index: 864763 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2336. Min Act: 0.0000

Data Index: 1639192 (Python Code)

Max Activating Token Index: 227

Text #6

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2293. Min Act: -0.0000

Data Index: 1456462 (Python Code)

Max Activating Token Index: 779

Text #7

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2209. Min Act: -0.0000

Data Index: 186188 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2133. Min Act: -0.0000

Data Index: 297853 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2141. Min Act: -0.0000

Data Index: 616876 (C4 (Web Text))

Max Activating Token Index: 472

Text #10

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2036. Min Act: 0.0000

Data Index: 1565433 (Python Code)

Max Activating Token Index: 558

Text #11

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2112. Min Act: 0.0000

Data Index: 1580903 (Python Code)

Max Activating Token Index: 30

Text #12

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2130. Min Act: -0.0000

Data Index: 1093875 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2252. Min Act: -0.0000

Data Index: 451285 (C4 (Web Text))

Max Activating Token Index: 326

Text #14

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.1940. Min Act: -0.0000

Data Index: 454084 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1556993 (Python Code)

Max Activating Token Index: 815

Text #16

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.1988. Min Act: -0.0000

Data Index: 467576 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.1902. Min Act: -0.0000

Data Index: 458846 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.1910. Min Act: -0.0000

Data Index: 1545803 (Python Code)

Max Activating Token Index: 526

Text #19

Max Range: 0.3774. Min Range: -0.3774

Max Act: 0.1946. Min Act: -0.0000

Data Index: 935501 (C4 (Web Text))

Max Activating Token Index: 888