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

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

Neuron 2371 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.8741. Min Range: -6.8741

Max Act: 6.8741. Min Act: -0.0000

Data Index: 1359768 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 6.8741. Min Range: -6.8741

Max Act: 6.4940. Min Act: -0.0000

Data Index: 589079 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 6.8741. Min Range: -6.8741

Max Act: 6.2051. Min Act: -0.0000

Data Index: 921225 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 6.8741. Min Range: -6.8741

Max Act: 5.9121. Min Act: -0.0000

Data Index: 660847 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 6.8741. Min Range: -6.8741

Max Act: 5.9947. Min Act: -0.0000

Data Index: 1266509 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 6.8741. Min Range: -6.8741

Max Act: 5.8139. Min Act: -0.0000

Data Index: 663901 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 6.8741. Min Range: -6.8741

Max Act: 5.6813. Min Act: -0.0000

Data Index: 601454 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 6.8741. Min Range: -6.8741

Max Act: 5.6204. Min Act: -0.0000

Data Index: 708059 (C4 (Web Text))

Max Activating Token Index: 481

Text #8

Max Range: 6.8741. Min Range: -6.8741

Max Act: 5.6378. Min Act: -0.0000

Data Index: 1296220 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 6.8741. Min Range: -6.8741

Max Act: 5.4567. Min Act: -0.0000

Data Index: 365568 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 6.8741. Min Range: -6.8741

Max Act: 5.3692. Min Act: -0.0000

Data Index: 322199 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 6.8741. Min Range: -6.8741

Max Act: 4.9818. Min Act: -0.0000

Data Index: 1202298 (C4 (Web Text))

Max Activating Token Index: 600

Text #12

Max Range: 6.8741. Min Range: -6.8741

Max Act: 5.2415. Min Act: -0.0000

Data Index: 231788 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 6.8741. Min Range: -6.8741

Max Act: 4.8247. Min Act: -0.0000

Data Index: 888887 (C4 (Web Text))

Max Activating Token Index: 538

Text #14

Max Range: 6.8741. Min Range: -6.8741

Max Act: 4.9852. Min Act: -0.0000

Data Index: 96249 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 6.8741. Min Range: -6.8741

Max Act: 4.9690. Min Act: -0.0000

Data Index: 604327 (C4 (Web Text))

Max Activating Token Index: 441

Text #16

Max Range: 6.8741. Min Range: -6.8741

Max Act: 5.1558. Min Act: -0.0000

Data Index: 439328 (C4 (Web Text))

Max Activating Token Index: 678

Text #17

Max Range: 6.8741. Min Range: -6.8741

Max Act: 5.1453. Min Act: -0.0000

Data Index: 893552 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 6.8741. Min Range: -6.8741

Max Act: 5.0737. Min Act: -0.0000

Data Index: 344319 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 6.8741. Min Range: -6.8741

Max Act: 5.0477. Min Act: -0.0000

Data Index: 21246 (C4 (Web Text))

Max Activating Token Index: 885