Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 853 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.0351. Min Range: -1.0351

Max Act: 1.0351. Min Act: -0.0000

Data Index: 72860 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 1.0351. Min Range: -1.0351

Max Act: 1.0300. Min Act: -0.0000

Data Index: 102592 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.9451. Min Act: -0.0000

Data Index: 283325 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.9641. Min Act: -0.0000

Data Index: 1272629 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.9048. Min Act: -0.0000

Data Index: 1328370 (C4 (Web Text))

Max Activating Token Index: 33

Text #5

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.8854. Min Act: -0.0000

Data Index: 385476 (C4 (Web Text))

Max Activating Token Index: 182

Text #6

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.9126. Min Act: -0.0000

Data Index: 267582 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.8107. Min Act: -0.0000

Data Index: 441864 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.7623. Min Act: -0.0000

Data Index: 957672 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.6853. Min Act: -0.0000

Data Index: 954545 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.6561. Min Act: -0.0000

Data Index: 238972 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.6992. Min Act: -0.0000

Data Index: 89086 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.6930. Min Act: -0.0000

Data Index: 575631 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.7086. Min Act: -0.0000

Data Index: 733776 (C4 (Web Text))

Max Activating Token Index: 334

Text #14

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.6856. Min Act: -0.0000

Data Index: 580444 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.6264. Min Act: -0.0000

Data Index: 147292 (C4 (Web Text))

Max Activating Token Index: 299

Text #16

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.6447. Min Act: -0.0000

Data Index: 428031 (C4 (Web Text))

Max Activating Token Index: 515

Text #17

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.6406. Min Act: -0.0000

Data Index: 336341 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1140274 (C4 (Web Text))

Max Activating Token Index: 619

Text #19

Max Range: 1.0351. Min Range: -1.0351

Max Act: 0.6577. Min Act: -0.0000

Data Index: 1019816 (C4 (Web Text))

Max Activating Token Index: 266