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

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

Neuron 4417 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.1032. Min Act: -0.0003

Data Index: 723794 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0588. Min Act: -0.0003

Data Index: 990922 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0567. Min Act: -0.0003

Data Index: 1304163 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0554. Min Act: -0.0003

Data Index: 485299 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0531. Min Act: -0.0003

Data Index: 264036 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0517. Min Act: -0.0002

Data Index: 627676 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0509. Min Act: -0.0003

Data Index: 525683 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0509. Min Act: -0.0003

Data Index: 1170503 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0516. Min Act: -0.0003

Data Index: 310983 (C4 (Web Text))

Max Activating Token Index: 779

Text #9

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0495. Min Act: -0.0003

Data Index: 697281 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0501. Min Act: -0.0002

Data Index: 850733 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0509. Min Act: -0.0003

Data Index: 867183 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0470. Min Act: -0.0002

Data Index: 1066583 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0488. Min Act: -0.0002

Data Index: 354063 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0462. Min Act: -0.0003

Data Index: 420331 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0474. Min Act: -0.0003

Data Index: 632445 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1142194 (C4 (Web Text))

Max Activating Token Index: 278

Text #17

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0476. Min Act: -0.0003

Data Index: 933342 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0480. Min Act: -0.0003

Data Index: 820660 (C4 (Web Text))

Max Activating Token Index: 827

Text #19

Max Range: 0.1032. Min Range: -0.1032

Max Act: 0.0468. Min Act: -0.0003

Data Index: 623066 (C4 (Web Text))

Max Activating Token Index: 377