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

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

Neuron 3115 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9372. Min Range: -4.9372

Max Act: 4.9372. Min Act: -0.0000

Data Index: 1011121 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 4.9372. Min Range: -4.9372

Max Act: 4.6922. Min Act: -0.0000

Data Index: 1107422 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 4.9372. Min Range: -4.9372

Max Act: 4.4647. Min Act: -0.0000

Data Index: 1123018 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 4.9372. Min Range: -4.9372

Max Act: 4.6563. Min Act: -0.0000

Data Index: 485054 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 4.9372. Min Range: -4.9372

Max Act: 4.8586. Min Act: -0.0000

Data Index: 887380 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 4.9372. Min Range: -4.9372

Max Act: 4.6324. Min Act: -0.0000

Data Index: 103418 (C4 (Web Text))

Max Activating Token Index: 89

Text #6

Max Range: 4.9372. Min Range: -4.9372

Max Act: 4.5770. Min Act: -0.0000

Data Index: 1077595 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 4.9372. Min Range: -4.9372

Max Act: 4.1486. Min Act: -0.0000

Data Index: 135628 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 4.9372. Min Range: -4.9372

Max Act: 4.1774. Min Act: -0.0000

Data Index: 1146659 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 4.9372. Min Range: -4.9372

Max Act: 4.0940. Min Act: -0.0000

Data Index: 126632 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 4.9372. Min Range: -4.9372

Max Act: 4.0256. Min Act: -0.0000

Data Index: 58247 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 4.9372. Min Range: -4.9372

Max Act: 3.9267. Min Act: -0.0000

Data Index: 1355208 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 4.9372. Min Range: -4.9372

Max Act: 3.8482. Min Act: -0.0000

Data Index: 5414 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 4.9372. Min Range: -4.9372

Max Act: 3.9607. Min Act: -0.0000

Data Index: 139019 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 4.9372. Min Range: -4.9372

Max Act: 3.8004. Min Act: -0.0000

Data Index: 692827 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 4.9372. Min Range: -4.9372

Max Act: 3.7357. Min Act: -0.0000

Data Index: 606541 (C4 (Web Text))

Max Activating Token Index: 775

Text #16

Max Range: 4.9372. Min Range: -4.9372

Max Act: 3.7539. Min Act: -0.0000

Data Index: 509444 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 4.9372. Min Range: -4.9372

Max Act: 3.7312. Min Act: -0.0000

Data Index: 114521 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 4.9372. Min Range: -4.9372

Max Act: 3.7057. Min Act: -0.0000

Data Index: 265626 (C4 (Web Text))

Max Activating Token Index: 470

Text #19

Max Range: 4.9372. Min Range: -4.9372

Max Act: 3.4655. Min Act: -0.0000

Data Index: 1261607 (C4 (Web Text))

Max Activating Token Index: 147