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

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

Neuron 1887 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0481. Min Range: -1.0481

Max Act: 1.0312. Min Act: -0.0000

Data Index: 1367555 (Python Code)

Max Activating Token Index: 390

Text #1

Max Range: 1.0481. Min Range: -1.0481

Max Act: 1.0481. Min Act: -0.0000

Data Index: 103831 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.9830. Min Act: -0.0000

Data Index: 1320800 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 1.0481. Min Range: -1.0481

Max Act: 1.0441. Min Act: -0.0000

Data Index: 830988 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.9858. Min Act: -0.0000

Data Index: 1185115 (C4 (Web Text))

Max Activating Token Index: 292

Text #5

Max Range: 1.0481. Min Range: -1.0481

Max Act: 1.0197. Min Act: -0.0000

Data Index: 1186451 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.9172. Min Act: -0.0000

Data Index: 438646 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.8872. Min Act: -0.0000

Data Index: 1437723 (Python Code)

Max Activating Token Index: 797

Text #8

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.8902. Min Act: -0.0000

Data Index: 857456 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.9178. Min Act: -0.0000

Data Index: 1224913 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.8420. Min Act: -0.0000

Data Index: 1413008 (Python Code)

Max Activating Token Index: 535

Text #11

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.8149. Min Act: -0.0000

Data Index: 222340 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.8202. Min Act: -0.0000

Data Index: 327709 (C4 (Web Text))

Max Activating Token Index: 859

Text #13

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.8101. Min Act: -0.0000

Data Index: 1144891 (C4 (Web Text))

Max Activating Token Index: 322

Text #14

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.8360. Min Act: -0.0000

Data Index: 1486727 (Python Code)

Max Activating Token Index: 323

Text #15

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.8052. Min Act: -0.0000

Data Index: 371702 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.8595. Min Act: -0.0000

Data Index: 985827 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.8424. Min Act: -0.0000

Data Index: 1514653 (Python Code)

Max Activating Token Index: 927

Text #18

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.7975. Min Act: -0.0000

Data Index: 1109805 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 1.0481. Min Range: -1.0481

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1102171 (C4 (Web Text))

Max Activating Token Index: 380