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

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

Neuron 4 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0837. Min Act: -0.0002

Data Index: 789537 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0809. Min Act: -0.0003

Data Index: 1020930 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0764. Min Act: -0.0003

Data Index: 558386 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0721. Min Act: -0.0002

Data Index: 1022901 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0709. Min Act: -0.0003

Data Index: 1207629 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0666. Min Act: -0.0002

Data Index: 281772 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0669. Min Act: -0.0003

Data Index: 241674 (C4 (Web Text))

Max Activating Token Index: 917

Text #7

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0643. Min Act: -0.0003

Data Index: 1262684 (C4 (Web Text))

Max Activating Token Index: 819

Text #8

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0666. Min Act: -0.0003

Data Index: 872299 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0604. Min Act: -0.0003

Data Index: 606329 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0621. Min Act: -0.0003

Data Index: 923530 (C4 (Web Text))

Max Activating Token Index: 416

Text #11

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0645. Min Act: -0.0002

Data Index: 978476 (C4 (Web Text))

Max Activating Token Index: 161

Text #12

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0605. Min Act: -0.0002

Data Index: 957376 (C4 (Web Text))

Max Activating Token Index: 510

Text #13

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0590. Min Act: -0.0003

Data Index: 512678 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0623. Min Act: -0.0003

Data Index: 920935 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0599. Min Act: -0.0003

Data Index: 134588 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0559. Min Act: -0.0003

Data Index: 892308 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0589. Min Act: -0.0002

Data Index: 996151 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0549. Min Act: -0.0003

Data Index: 1109657 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.0837. Min Range: -0.0837

Max Act: 0.0578. Min Act: -0.0002

Data Index: 891682 (C4 (Web Text))

Max Activating Token Index: 470