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

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

Neuron 116 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5729. Min Range: -1.5729

Max Act: 1.5729. Min Act: -0.0000

Data Index: 1241715 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 1.5729. Min Range: -1.5729

Max Act: 1.4454. Min Act: -0.0000

Data Index: 246673 (C4 (Web Text))

Max Activating Token Index: 422

Text #2

Max Range: 1.5729. Min Range: -1.5729

Max Act: 1.3150. Min Act: -0.0000

Data Index: 941405 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 1.5729. Min Range: -1.5729

Max Act: 1.3363. Min Act: -0.0000

Data Index: 776402 (C4 (Web Text))

Max Activating Token Index: 676

Text #4

Max Range: 1.5729. Min Range: -1.5729

Max Act: 1.2412. Min Act: -0.0000

Data Index: 320284 (C4 (Web Text))

Max Activating Token Index: 145

Text #5

Max Range: 1.5729. Min Range: -1.5729

Max Act: 1.1706. Min Act: -0.0000

Data Index: 425653 (C4 (Web Text))

Max Activating Token Index: 416

Text #6

Max Range: 1.5729. Min Range: -1.5729

Max Act: 1.2232. Min Act: -0.0000

Data Index: 805933 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 1.5729. Min Range: -1.5729

Max Act: 1.1633. Min Act: -0.0001

Data Index: 357705 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 1.5729. Min Range: -1.5729

Max Act: 1.0390. Min Act: -0.0000

Data Index: 697503 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 1.5729. Min Range: -1.5729

Max Act: 1.0860. Min Act: -0.0000

Data Index: 803921 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 1.5729. Min Range: -1.5729

Max Act: 1.0316. Min Act: -0.0000

Data Index: 127733 (C4 (Web Text))

Max Activating Token Index: 532

Text #11

Max Range: 1.5729. Min Range: -1.5729

Max Act: 0.9472. Min Act: -0.0001

Data Index: 712750 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 1.5729. Min Range: -1.5729

Max Act: 1.0470. Min Act: -0.0000

Data Index: 566461 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 1.5729. Min Range: -1.5729

Max Act: 0.9752. Min Act: -0.0000

Data Index: 49569 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 1.5729. Min Range: -1.5729

Max Act: 0.9359. Min Act: -0.0000

Data Index: 1315117 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 1.5729. Min Range: -1.5729

Max Act: 0.9460. Min Act: -0.0000

Data Index: 828609 (C4 (Web Text))

Max Activating Token Index: 130

Text #16

Max Range: 1.5729. Min Range: -1.5729

Max Act: 0.9010. Min Act: -0.0000

Data Index: 292071 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 1.5729. Min Range: -1.5729

Max Act: 0.9488. Min Act: -0.0000

Data Index: 316878 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 1.5729. Min Range: -1.5729

Max Act: 1.0320. Min Act: -0.0000

Data Index: 1127997 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 1.5729. Min Range: -1.5729

Max Act: 0.9469. Min Act: -0.0001

Data Index: 1291598 (C4 (Web Text))

Max Activating Token Index: 566