Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 20 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0715. Min Act: -0.0005

Data Index: 934185 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0643. Min Act: -0.0005

Data Index: 579923 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0615. Min Act: -0.0005

Data Index: 625171 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0606. Min Act: -0.0005

Data Index: 679974 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0614. Min Act: -0.0005

Data Index: 648486 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0596. Min Act: -0.0005

Data Index: 1066875 (C4 (Web Text))

Max Activating Token Index: 410

Text #6

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0608. Min Act: -0.0005

Data Index: 1254300 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0607. Min Act: -0.0005

Data Index: 920294 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0607. Min Act: -0.0005

Data Index: 154785 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0588. Min Act: -0.0005

Data Index: 1185897 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0597. Min Act: -0.0005

Data Index: 1078012 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0583. Min Act: -0.0005

Data Index: 1181982 (C4 (Web Text))

Max Activating Token Index: 115

Text #12

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0591. Min Act: -0.0005

Data Index: 445489 (C4 (Web Text))

Max Activating Token Index: 120

Text #13

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0582. Min Act: -0.0005

Data Index: 960732 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0589. Min Act: -0.0005

Data Index: 652266 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0578. Min Act: -0.0005

Data Index: 470035 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0564. Min Act: -0.0006

Data Index: 916462 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0556. Min Act: -0.0005

Data Index: 751669 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0567. Min Act: -0.0005

Data Index: 885221 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.0715. Min Range: -0.0715

Max Act: 0.0566. Min Act: -0.0005

Data Index: 814023 (C4 (Web Text))

Max Activating Token Index: 39