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

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

Neuron 4119 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9003. Min Range: -1.9003

Max Act: 1.7804. Min Act: -0.0000

Data Index: 776986 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 1.9003. Min Range: -1.9003

Max Act: 1.9003. Min Act: -0.0000

Data Index: 279796 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 1.9003. Min Range: -1.9003

Max Act: 1.6289. Min Act: -0.0000

Data Index: 12119 (C4 (Web Text))

Max Activating Token Index: 353

Text #3

Max Range: 1.9003. Min Range: -1.9003

Max Act: 1.6192. Min Act: -0.0000

Data Index: 478454 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 1.9003. Min Range: -1.9003

Max Act: 1.7197. Min Act: -0.0000

Data Index: 1059924 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 1.9003. Min Range: -1.9003

Max Act: 1.6097. Min Act: -0.0000

Data Index: 1285032 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 1.9003. Min Range: -1.9003

Max Act: 1.3884. Min Act: -0.0000

Data Index: 1326362 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 1.9003. Min Range: -1.9003

Max Act: 1.5492. Min Act: -0.0000

Data Index: 383021 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 1.9003. Min Range: -1.9003

Max Act: 1.5055. Min Act: -0.0000

Data Index: 1176830 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 1.9003. Min Range: -1.9003

Max Act: 1.4074. Min Act: -0.0000

Data Index: 541325 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 1.9003. Min Range: -1.9003

Max Act: 1.5088. Min Act: -0.0000

Data Index: 967859 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 1.9003. Min Range: -1.9003

Max Act: 1.4611. Min Act: -0.0000

Data Index: 98609 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 1.9003. Min Range: -1.9003

Max Act: 1.4249. Min Act: -0.0000

Data Index: 1008814 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 1.9003. Min Range: -1.9003

Max Act: 1.4127. Min Act: -0.0000

Data Index: 204188 (C4 (Web Text))

Max Activating Token Index: 87

Text #14

Max Range: 1.9003. Min Range: -1.9003

Max Act: 1.3787. Min Act: -0.0000

Data Index: 559552 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 1.9003. Min Range: -1.9003

Max Act: 1.2787. Min Act: -0.0000

Data Index: 68087 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 1.9003. Min Range: -1.9003

Max Act: 1.2921. Min Act: -0.0000

Data Index: 1410540 (Python Code)

Max Activating Token Index: 492

Text #17

Max Range: 1.9003. Min Range: -1.9003

Max Act: 1.3008. Min Act: -0.0000

Data Index: 676401 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 1.9003. Min Range: -1.9003

Max Act: 1.2243. Min Act: -0.0000

Data Index: 602622 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 1.9003. Min Range: -1.9003

Max Act: 1.2267. Min Act: -0.0000

Data Index: 1641018 (Python Code)

Max Activating Token Index: 392