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

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

Neuron 5857 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: 1.4736. Min Range: -1.4736

Max Act: 1.4736. Min Act: -0.0000

Data Index: 89010 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.2593. Min Act: -0.0000

Data Index: 1339448 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.2191. Min Act: -0.0000

Data Index: 573598 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.1699. Min Act: -0.0000

Data Index: 612875 (C4 (Web Text))

Max Activating Token Index: 822

Text #4

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.1689. Min Act: -0.0000

Data Index: 441043 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.1575. Min Act: -0.0000

Data Index: 839803 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.1101. Min Act: -0.0000

Data Index: 1347872 (C4 (Web Text))

Max Activating Token Index: 476

Text #7

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.0946. Min Act: -0.0000

Data Index: 1340940 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.0617. Min Act: -0.0000

Data Index: 265676 (C4 (Web Text))

Max Activating Token Index: 279

Text #9

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.0574. Min Act: -0.0000

Data Index: 799438 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.0578. Min Act: -0.0000

Data Index: 1039413 (C4 (Web Text))

Max Activating Token Index: 564

Text #11

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.0389. Min Act: -0.0000

Data Index: 985086 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.0308. Min Act: -0.0000

Data Index: 446897 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 1.4736. Min Range: -1.4736

Max Act: 1.0263. Min Act: -0.0000

Data Index: 577652 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 1.4736. Min Range: -1.4736

Max Act: 0.9975. Min Act: -0.0000

Data Index: 66981 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 1.4736. Min Range: -1.4736

Max Act: 0.9957. Min Act: -0.0000

Data Index: 440366 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 1.4736. Min Range: -1.4736

Max Act: 0.9340. Min Act: -0.0000

Data Index: 885672 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 1.4736. Min Range: -1.4736

Max Act: 0.9815. Min Act: -0.0000

Data Index: 387550 (C4 (Web Text))

Max Activating Token Index: 409

Text #18

Max Range: 1.4736. Min Range: -1.4736

Max Act: 0.9728. Min Act: -0.0000

Data Index: 584048 (C4 (Web Text))

Max Activating Token Index: 458

Text #19

Max Range: 1.4736. Min Range: -1.4736

Max Act: 0.9595. Min Act: -0.0000

Data Index: 632502 (C4 (Web Text))

Max Activating Token Index: 705