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

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

Neuron 1624 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0793. Min Range: -3.0793

Max Act: 3.0790. Min Act: -0.0000

Data Index: 1437179 (Python Code)

Max Activating Token Index: 588

Text #1

Max Range: 3.0793. Min Range: -3.0793

Max Act: 2.9955. Min Act: -0.0000

Data Index: 1102082 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 3.0793. Min Range: -3.0793

Max Act: 2.8487. Min Act: -0.0000

Data Index: 184892 (C4 (Web Text))

Max Activating Token Index: 254

Text #3

Max Range: 3.0793. Min Range: -3.0793

Max Act: 2.9679. Min Act: -0.0000

Data Index: 70322 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 3.0793. Min Range: -3.0793

Max Act: 3.0793. Min Act: -0.0000

Data Index: 1375373 (Python Code)

Max Activating Token Index: 634

Text #5

Max Range: 3.0793. Min Range: -3.0793

Max Act: 2.7894. Min Act: -0.0000

Data Index: 223906 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 3.0793. Min Range: -3.0793

Max Act: 2.9088. Min Act: -0.0000

Data Index: 1017566 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 3.0793. Min Range: -3.0793

Max Act: 2.6871. Min Act: -0.0000

Data Index: 1641692 (Python Code)

Max Activating Token Index: 198

Text #8

Max Range: 3.0793. Min Range: -3.0793

Max Act: 2.7745. Min Act: -0.0000

Data Index: 30938 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 3.0793. Min Range: -3.0793

Max Act: 2.6140. Min Act: -0.0000

Data Index: 803652 (C4 (Web Text))

Max Activating Token Index: 712

Text #10

Max Range: 3.0793. Min Range: -3.0793

Max Act: 2.7142. Min Act: -0.0000

Data Index: 1475406 (Python Code)

Max Activating Token Index: 817

Text #11

Max Range: 3.0793. Min Range: -3.0793

Max Act: 2.6589. Min Act: -0.0000

Data Index: 646471 (C4 (Web Text))

Max Activating Token Index: 204

Text #12

Max Range: 3.0793. Min Range: -3.0793

Max Act: 2.6556. Min Act: -0.0000

Data Index: 182673 (C4 (Web Text))

Max Activating Token Index: 310

Text #13

Max Range: 3.0793. Min Range: -3.0793

Max Act: 2.6599. Min Act: -0.0000

Data Index: 1164152 (C4 (Web Text))

Max Activating Token Index: 596

Text #14

Max Range: 3.0793. Min Range: -3.0793

Max Act: 2.7656. Min Act: -0.0000

Data Index: 5410 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 3.0793. Min Range: -3.0793

Max Act: 2.5954. Min Act: -0.0000

Data Index: 306247 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 3.0793. Min Range: -3.0793

Max Act: 2.5724. Min Act: -0.0000

Data Index: 894406 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 3.0793. Min Range: -3.0793

Max Act: 2.4337. Min Act: -0.0000

Data Index: 1366438 (Python Code)

Max Activating Token Index: 278

Text #18

Max Range: 3.0793. Min Range: -3.0793

Max Act: 2.6614. Min Act: -0.0000

Data Index: 1397832 (Python Code)

Max Activating Token Index: 823

Text #19

Max Range: 3.0793. Min Range: -3.0793

Max Act: 2.4960. Min Act: -0.0000

Data Index: 1340639 (C4 (Web Text))

Max Activating Token Index: 584