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

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

Neuron 5493 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: 2.7589. Min Range: -2.7589

Max Act: 2.7589. Min Act: -0.0000

Data Index: 334625 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 2.7589. Min Range: -2.7589

Max Act: 2.6966. Min Act: -0.0000

Data Index: 509479 (C4 (Web Text))

Max Activating Token Index: 436

Text #2

Max Range: 2.7589. Min Range: -2.7589

Max Act: 2.1261. Min Act: -0.0000

Data Index: 647569 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 2.7589. Min Range: -2.7589

Max Act: 2.4323. Min Act: -0.0000

Data Index: 155408 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 2.7589. Min Range: -2.7589

Max Act: 2.1660. Min Act: -0.0000

Data Index: 388969 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 2.7589. Min Range: -2.7589

Max Act: 2.1229. Min Act: -0.0000

Data Index: 290444 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 2.7589. Min Range: -2.7589

Max Act: 2.1194. Min Act: -0.0000

Data Index: 765815 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 2.7589. Min Range: -2.7589

Max Act: 1.9887. Min Act: -0.0000

Data Index: 374621 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 2.7589. Min Range: -2.7589

Max Act: 2.1033. Min Act: -0.0000

Data Index: 1248261 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 2.7589. Min Range: -2.7589

Max Act: 1.7680. Min Act: -0.0000

Data Index: 548899 (C4 (Web Text))

Max Activating Token Index: 683

Text #10

Max Range: 2.7589. Min Range: -2.7589

Max Act: 1.8629. Min Act: -0.0000

Data Index: 285779 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 2.7589. Min Range: -2.7589

Max Act: 1.8619. Min Act: -0.0000

Data Index: 685228 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 2.7589. Min Range: -2.7589

Max Act: 1.7597. Min Act: -0.0000

Data Index: 310118 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 2.7589. Min Range: -2.7589

Max Act: 1.8344. Min Act: -0.0000

Data Index: 1519885 (Python Code)

Max Activating Token Index: 254

Text #14

Max Range: 2.7589. Min Range: -2.7589

Max Act: 1.5770. Min Act: -0.0000

Data Index: 1173715 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 2.7589. Min Range: -2.7589

Max Act: 1.8136. Min Act: -0.0000

Data Index: 944655 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 2.7589. Min Range: -2.7589

Max Act: 1.8134. Min Act: -0.0000

Data Index: 3115 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 2.7589. Min Range: -2.7589

Max Act: 1.7432. Min Act: -0.0000

Data Index: 107496 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 2.7589. Min Range: -2.7589

Max Act: 1.6910. Min Act: -0.0000

Data Index: 85527 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 2.7589. Min Range: -2.7589

Max Act: 1.8800. Min Act: -0.0000

Data Index: 336348 (C4 (Web Text))

Max Activating Token Index: 835