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

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

Neuron 4764 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2245. Min Act: -0.0000

Data Index: 297834 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2785. Min Act: -0.0000

Data Index: 1229690 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2361. Min Act: -0.0000

Data Index: 1351524 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2144. Min Act: -0.0000

Data Index: 79746 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2270. Min Act: -0.0000

Data Index: 443268 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2206. Min Act: -0.0000

Data Index: 506434 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2014. Min Act: -0.0000

Data Index: 1331251 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2067. Min Act: -0.0000

Data Index: 472262 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2162. Min Act: -0.0000

Data Index: 174933 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.1994. Min Act: -0.0000

Data Index: 1136000 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2106. Min Act: -0.0000

Data Index: 1211940 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2030. Min Act: -0.0000

Data Index: 878432 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2114. Min Act: -0.0000

Data Index: 605050 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2051. Min Act: -0.0000

Data Index: 1208852 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2047. Min Act: -0.0000

Data Index: 553621 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1050033 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2009. Min Act: -0.0000

Data Index: 195782 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.1937. Min Act: -0.0000

Data Index: 355868 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.2027. Min Act: -0.0000

Data Index: 1329253 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 0.2785. Min Range: -0.2785

Max Act: 0.1930. Min Act: -0.0000

Data Index: 1218078 (C4 (Web Text))

Max Activating Token Index: 1015