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

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

Neuron 643 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0672. Min Act: -0.0005

Data Index: 3655 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0567. Min Act: -0.0005

Data Index: 856273 (C4 (Web Text))

Max Activating Token Index: 459

Text #2

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0671. Min Act: -0.0005

Data Index: 256191 (C4 (Web Text))

Max Activating Token Index: 509

Text #3

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0639. Min Act: -0.0005

Data Index: 969753 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0638. Min Act: -0.0004

Data Index: 154585 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0609. Min Act: -0.0005

Data Index: 188892 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0599. Min Act: -0.0005

Data Index: 649603 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0600. Min Act: -0.0005

Data Index: 700759 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0606. Min Act: -0.0005

Data Index: 906743 (C4 (Web Text))

Max Activating Token Index: 863

Text #9

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0577. Min Act: -0.0005

Data Index: 769071 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0616. Min Act: -0.0005

Data Index: 836500 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0564. Min Act: -0.0005

Data Index: 524877 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0608. Min Act: -0.0005

Data Index: 352562 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0605. Min Act: -0.0005

Data Index: 669000 (C4 (Web Text))

Max Activating Token Index: 788

Text #14

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0507. Min Act: -0.0005

Data Index: 831606 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0577. Min Act: -0.0005

Data Index: 211748 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0558. Min Act: -0.0005

Data Index: 606116 (C4 (Web Text))

Max Activating Token Index: 404

Text #17

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0599. Min Act: -0.0005

Data Index: 1187239 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0610. Min Act: -0.0005

Data Index: 627581 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.0672. Min Range: -0.0672

Max Act: 0.0575. Min Act: -0.0005

Data Index: 1002897 (C4 (Web Text))

Max Activating Token Index: 655