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

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

Neuron 658 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3889. Min Range: -2.3889

Max Act: 2.3889. Min Act: -0.0000

Data Index: 209331 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 2.3889. Min Range: -2.3889

Max Act: 2.1055. Min Act: -0.0000

Data Index: 736340 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 2.3889. Min Range: -2.3889

Max Act: 1.9645. Min Act: -0.0000

Data Index: 173862 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 2.3889. Min Range: -2.3889

Max Act: 2.1573. Min Act: -0.0000

Data Index: 833881 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 2.3889. Min Range: -2.3889

Max Act: 2.0570. Min Act: -0.0000

Data Index: 1580587 (Python Code)

Max Activating Token Index: 818

Text #5

Max Range: 2.3889. Min Range: -2.3889

Max Act: 2.0076. Min Act: -0.0000

Data Index: 127191 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 2.3889. Min Range: -2.3889

Max Act: 1.7829. Min Act: -0.0000

Data Index: 655592 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 2.3889. Min Range: -2.3889

Max Act: 1.9685. Min Act: -0.0000

Data Index: 1145362 (C4 (Web Text))

Max Activating Token Index: 778

Text #8

Max Range: 2.3889. Min Range: -2.3889

Max Act: 1.8837. Min Act: -0.0000

Data Index: 551729 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 2.3889. Min Range: -2.3889

Max Act: 1.9688. Min Act: -0.0000

Data Index: 1351623 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 2.3889. Min Range: -2.3889

Max Act: 1.8479. Min Act: -0.0000

Data Index: 662286 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 2.3889. Min Range: -2.3889

Max Act: 1.8459. Min Act: -0.0000

Data Index: 1543624 (Python Code)

Max Activating Token Index: 41

Text #12

Max Range: 2.3889. Min Range: -2.3889

Max Act: 1.8322. Min Act: -0.0000

Data Index: 1352323 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 2.3889. Min Range: -2.3889

Max Act: 1.8165. Min Act: -0.0000

Data Index: 862049 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 2.3889. Min Range: -2.3889

Max Act: 1.8987. Min Act: -0.0000

Data Index: 1485453 (Python Code)

Max Activating Token Index: 905

Text #15

Max Range: 2.3889. Min Range: -2.3889

Max Act: 1.8702. Min Act: -0.0000

Data Index: 897836 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 2.3889. Min Range: -2.3889

Max Act: 1.7307. Min Act: -0.0000

Data Index: 1265005 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 2.3889. Min Range: -2.3889

Max Act: 1.8161. Min Act: -0.0000

Data Index: 12342 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 2.3889. Min Range: -2.3889

Max Act: 1.8955. Min Act: -0.0000

Data Index: 637781 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 2.3889. Min Range: -2.3889

Max Act: 1.7100. Min Act: -0.0000

Data Index: 251822 (C4 (Web Text))

Max Activating Token Index: 163