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

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

Neuron 787 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.3065. Min Act: -0.0001

Data Index: 1269787 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2627. Min Act: -0.0001

Data Index: 382844 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2845. Min Act: -0.0001

Data Index: 591591 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2543. Min Act: -0.0001

Data Index: 295869 (C4 (Web Text))

Max Activating Token Index: 871

Text #4

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2346. Min Act: -0.0001

Data Index: 777411 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2297. Min Act: -0.0001

Data Index: 209858 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2445. Min Act: -0.0001

Data Index: 1061977 (C4 (Web Text))

Max Activating Token Index: 617

Text #7

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2313. Min Act: -0.0001

Data Index: 418081 (C4 (Web Text))

Max Activating Token Index: 157

Text #8

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2245. Min Act: -0.0001

Data Index: 544557 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2361. Min Act: -0.0001

Data Index: 648898 (C4 (Web Text))

Max Activating Token Index: 792

Text #10

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2274. Min Act: -0.0001

Data Index: 1245466 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2187. Min Act: -0.0001

Data Index: 1075947 (C4 (Web Text))

Max Activating Token Index: 27

Text #12

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2116. Min Act: -0.0001

Data Index: 575883 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2043. Min Act: -0.0001

Data Index: 105474 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2042. Min Act: -0.0001

Data Index: 404354 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2110. Min Act: -0.0001

Data Index: 1215511 (C4 (Web Text))

Max Activating Token Index: 33

Text #16

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2191. Min Act: -0.0001

Data Index: 21357 (C4 (Web Text))

Max Activating Token Index: 384

Text #17

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2069. Min Act: -0.0001

Data Index: 186354 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2045. Min Act: -0.0001

Data Index: 648801 (C4 (Web Text))

Max Activating Token Index: 933

Text #19

Max Range: 0.3065. Min Range: -0.3065

Max Act: 0.2000. Min Act: -0.0001

Data Index: 1034580 (C4 (Web Text))

Max Activating Token Index: 728