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

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

Neuron 4232 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: 0.9657. Min Range: -0.9657

Max Act: 0.9657. Min Act: -0.0000

Data Index: 967918 (C4 (Web Text))

Max Activating Token Index: 721

Text #1

Max Range: 0.9657. Min Range: -0.9657

Max Act: 0.9353. Min Act: -0.0000

Data Index: 309789 (C4 (Web Text))

Max Activating Token Index: 495

Text #2

Max Range: 0.9657. Min Range: -0.9657

Max Act: 0.9191. Min Act: -0.0000

Data Index: 71402 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 0.9657. Min Range: -0.9657

Max Act: 0.8816. Min Act: -0.0000

Data Index: 259529 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.9657. Min Range: -0.9657

Max Act: 0.8229. Min Act: -0.0000

Data Index: 1204985 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.9657. Min Range: -0.9657

Max Act: 0.8706. Min Act: -0.0000

Data Index: 75778 (C4 (Web Text))

Max Activating Token Index: 764

Text #6

Max Range: 0.9657. Min Range: -0.9657

Max Act: 0.7765. Min Act: -0.0000

Data Index: 1092386 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 0.9657. Min Range: -0.9657

Max Act: 0.8623. Min Act: -0.0000

Data Index: 84793 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.9657. Min Range: -0.9657

Max Act: 0.7805. Min Act: -0.0000

Data Index: 192498 (C4 (Web Text))

Max Activating Token Index: 125

Text #9

Max Range: 0.9657. Min Range: -0.9657

Max Act: 0.8209. Min Act: -0.0000

Data Index: 541138 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.9657. Min Range: -0.9657

Max Act: 0.7696. Min Act: -0.0000

Data Index: 230121 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.9657. Min Range: -0.9657

Max Act: 0.7866. Min Act: -0.0000

Data Index: 438764 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.9657. Min Range: -0.9657

Max Act: 0.7817. Min Act: -0.0000

Data Index: 693698 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 0.9657. Min Range: -0.9657

Max Act: 0.8333. Min Act: -0.0000

Data Index: 156536 (C4 (Web Text))

Max Activating Token Index: 806

Text #14

Max Range: 0.9657. Min Range: -0.9657

Max Act: 0.8511. Min Act: -0.0000

Data Index: 723661 (C4 (Web Text))

Max Activating Token Index: 586

Text #15

Max Range: 0.9657. Min Range: -0.9657

Max Act: 0.8186. Min Act: -0.0000

Data Index: 670568 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 0.9657. Min Range: -0.9657

Max Act: 0.7676. Min Act: -0.0000

Data Index: 1321981 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 0.9657. Min Range: -0.9657

Max Act: 0.7839. Min Act: -0.0000

Data Index: 927330 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 0.9657. Min Range: -0.9657

Max Act: 0.7592. Min Act: -0.0000

Data Index: 138134 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.9657. Min Range: -0.9657

Max Act: 0.8053. Min Act: -0.0000

Data Index: 243898 (C4 (Web Text))

Max Activating Token Index: 771