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

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

Neuron 147 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: 0.0851. Min Range: -0.0851

Max Act: 0.0851. Min Act: -0.0005

Data Index: 1239271 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0751. Min Act: -0.0005

Data Index: 1101436 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0792. Min Act: -0.0005

Data Index: 331712 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0784. Min Act: -0.0005

Data Index: 648508 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0806. Min Act: -0.0005

Data Index: 647901 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0770. Min Act: -0.0005

Data Index: 258503 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0719. Min Act: -0.0005

Data Index: 713903 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0726. Min Act: -0.0005

Data Index: 760676 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0685. Min Act: -0.0005

Data Index: 649553 (C4 (Web Text))

Max Activating Token Index: 575

Text #9

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0724. Min Act: -0.0005

Data Index: 1159471 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0706. Min Act: -0.0005

Data Index: 210325 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0710. Min Act: -0.0005

Data Index: 1032457 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0707. Min Act: -0.0005

Data Index: 1315189 (C4 (Web Text))

Max Activating Token Index: 390

Text #13

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0695. Min Act: -0.0005

Data Index: 331470 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0654. Min Act: -0.0005

Data Index: 280215 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0702. Min Act: -0.0005

Data Index: 1161555 (C4 (Web Text))

Max Activating Token Index: 751

Text #16

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0702. Min Act: -0.0005

Data Index: 1261188 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0661. Min Act: -0.0005

Data Index: 592482 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0718. Min Act: -0.0005

Data Index: 514534 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.0851. Min Range: -0.0851

Max Act: 0.0667. Min Act: -0.0005

Data Index: 914578 (C4 (Web Text))

Max Activating Token Index: 740