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

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

Neuron 1947 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: 0.6351. Min Range: -0.6351

Max Act: 0.6247. Min Act: -0.0000

Data Index: 986522 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.6063. Min Act: -0.0000

Data Index: 635007 (C4 (Web Text))

Max Activating Token Index: 512

Text #2

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.6351. Min Act: -0.0000

Data Index: 974584 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5714. Min Act: -0.0000

Data Index: 515119 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5227. Min Act: -0.0000

Data Index: 366062 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5563. Min Act: -0.0000

Data Index: 455223 (C4 (Web Text))

Max Activating Token Index: 391

Text #6

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5226. Min Act: -0.0000

Data Index: 1105564 (C4 (Web Text))

Max Activating Token Index: 976

Text #7

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4836. Min Act: -0.0000

Data Index: 1193155 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5094. Min Act: -0.0000

Data Index: 1176540 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5118. Min Act: -0.0000

Data Index: 564407 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4945. Min Act: -0.0000

Data Index: 532208 (C4 (Web Text))

Max Activating Token Index: 490

Text #11

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5078. Min Act: -0.0000

Data Index: 1331236 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4822. Min Act: -0.0000

Data Index: 243514 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4919. Min Act: -0.0000

Data Index: 1253544 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5074. Min Act: -0.0000

Data Index: 497349 (C4 (Web Text))

Max Activating Token Index: 839

Text #15

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4900. Min Act: -0.0000

Data Index: 1191824 (C4 (Web Text))

Max Activating Token Index: 407

Text #16

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4904. Min Act: -0.0000

Data Index: 119917 (C4 (Web Text))

Max Activating Token Index: 117

Text #17

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.5234. Min Act: -0.0000

Data Index: 1320098 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4643. Min Act: -0.0000

Data Index: 766787 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 0.6351. Min Range: -0.6351

Max Act: 0.4832. Min Act: -0.0000

Data Index: 934072 (C4 (Web Text))

Max Activating Token Index: 411