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

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

Neuron 3028 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: 0.0844. Min Range: -0.0844

Max Act: 0.0844. Min Act: -0.0000

Data Index: 779719 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0830. Min Act: -0.0000

Data Index: 732768 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0548. Min Act: -0.0000

Data Index: 25469 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0634. Min Act: -0.0000

Data Index: 652882 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0642. Min Act: -0.0000

Data Index: 20515 (C4 (Web Text))

Max Activating Token Index: 711

Text #5

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0633. Min Act: -0.0000

Data Index: 1329920 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0619. Min Act: -0.0000

Data Index: 485978 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0666. Min Act: -0.0000

Data Index: 329539 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0632. Min Act: -0.0000

Data Index: 1345529 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0603. Min Act: -0.0000

Data Index: 790737 (C4 (Web Text))

Max Activating Token Index: 880

Text #10

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0599. Min Act: -0.0000

Data Index: 876954 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0500. Min Act: -0.0000

Data Index: 815717 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0543. Min Act: -0.0000

Data Index: 806823 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0567. Min Act: -0.0000

Data Index: 1175042 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0562. Min Act: -0.0000

Data Index: 917083 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0546. Min Act: -0.0000

Data Index: 508810 (C4 (Web Text))

Max Activating Token Index: 741

Text #16

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0540. Min Act: -0.0000

Data Index: 484816 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0519. Min Act: -0.0000

Data Index: 704851 (C4 (Web Text))

Max Activating Token Index: 201

Text #18

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0536. Min Act: -0.0000

Data Index: 216885 (C4 (Web Text))

Max Activating Token Index: 348

Text #19

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0514. Min Act: -0.0000

Data Index: 1143313 (C4 (Web Text))

Max Activating Token Index: 59