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

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

Neuron 4202 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4379. Min Range: -2.4379

Max Act: 2.3269. Min Act: -0.0000

Data Index: 620259 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 2.4379. Min Range: -2.4379

Max Act: 2.4379. Min Act: -0.0000

Data Index: 357331 (C4 (Web Text))

Max Activating Token Index: 726

Text #2

Max Range: 2.4379. Min Range: -2.4379

Max Act: 2.2657. Min Act: -0.0000

Data Index: 142277 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 2.4379. Min Range: -2.4379

Max Act: 2.3745. Min Act: -0.0000

Data Index: 1124903 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 2.4379. Min Range: -2.4379

Max Act: 2.1176. Min Act: -0.0000

Data Index: 1175006 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 2.4379. Min Range: -2.4379

Max Act: 2.2308. Min Act: -0.0000

Data Index: 448244 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 2.4379. Min Range: -2.4379

Max Act: 2.2059. Min Act: -0.0000

Data Index: 21805 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 2.4379. Min Range: -2.4379

Max Act: 2.2028. Min Act: -0.0000

Data Index: 111503 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 2.4379. Min Range: -2.4379

Max Act: 2.2053. Min Act: -0.0000

Data Index: 1093862 (C4 (Web Text))

Max Activating Token Index: 1018

Text #9

Max Range: 2.4379. Min Range: -2.4379

Max Act: 2.2086. Min Act: -0.0000

Data Index: 770941 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 2.4379. Min Range: -2.4379

Max Act: 2.1350. Min Act: -0.0000

Data Index: 196320 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 2.4379. Min Range: -2.4379

Max Act: 2.2460. Min Act: -0.0000

Data Index: 1030461 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 2.4379. Min Range: -2.4379

Max Act: 1.8838. Min Act: -0.0000

Data Index: 656539 (C4 (Web Text))

Max Activating Token Index: 633

Text #13

Max Range: 2.4379. Min Range: -2.4379

Max Act: 2.1876. Min Act: -0.0000

Data Index: 242705 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 2.4379. Min Range: -2.4379

Max Act: 1.9264. Min Act: -0.0000

Data Index: 215554 (C4 (Web Text))

Max Activating Token Index: 694

Text #15

Max Range: 2.4379. Min Range: -2.4379

Max Act: 2.0126. Min Act: -0.0000

Data Index: 11192 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 2.4379. Min Range: -2.4379

Max Act: 2.1462. Min Act: -0.0000

Data Index: 1012352 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 2.4379. Min Range: -2.4379

Max Act: 1.9984. Min Act: -0.0000

Data Index: 1098466 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 2.4379. Min Range: -2.4379

Max Act: 1.8429. Min Act: -0.0000

Data Index: 54876 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 2.4379. Min Range: -2.4379

Max Act: 2.0287. Min Act: -0.0000

Data Index: 479675 (C4 (Web Text))

Max Activating Token Index: 773