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

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

Neuron 711 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0854. Min Act: -0.0002

Data Index: 567730 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0842. Min Act: -0.0002

Data Index: 570819 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0822. Min Act: -0.0002

Data Index: 853121 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0773. Min Act: -0.0002

Data Index: 62556 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0765. Min Act: -0.0002

Data Index: 291707 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0699. Min Act: -0.0002

Data Index: 499653 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0705. Min Act: -0.0002

Data Index: 190574 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0666. Min Act: -0.0002

Data Index: 664309 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0717. Min Act: -0.0002

Data Index: 384355 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1357247 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0664. Min Act: -0.0002

Data Index: 1334065 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0670. Min Act: -0.0002

Data Index: 1099706 (C4 (Web Text))

Max Activating Token Index: 455

Text #12

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0667. Min Act: -0.0002

Data Index: 1013157 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1063154 (C4 (Web Text))

Max Activating Token Index: 945

Text #14

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0686. Min Act: -0.0002

Data Index: 242773 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1471896 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0684. Min Act: -0.0002

Data Index: 34798 (C4 (Web Text))

Max Activating Token Index: 500

Text #17

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0685. Min Act: -0.0002

Data Index: 672067 (C4 (Web Text))

Max Activating Token Index: 852

Text #18

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0654. Min Act: -0.0002

Data Index: 31035 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.0854. Min Range: -0.0854

Max Act: 0.0679. Min Act: -0.0001

Data Index: 1501153 (Python Code)

Max Activating Token Index: 713