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

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

Neuron 834 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.1037. Min Act: -0.0006

Data Index: 480568 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0899. Min Act: -0.0006

Data Index: 896582 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0847. Min Act: -0.0006

Data Index: 1145359 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0812. Min Act: -0.0006

Data Index: 383058 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0768. Min Act: -0.0006

Data Index: 526941 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0716. Min Act: -0.0006

Data Index: 538200 (C4 (Web Text))

Max Activating Token Index: 257

Text #6

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0624. Min Act: -0.0006

Data Index: 613522 (C4 (Web Text))

Max Activating Token Index: 887

Text #7

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0675. Min Act: -0.0006

Data Index: 670381 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0692. Min Act: -0.0006

Data Index: 144798 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0684. Min Act: -0.0006

Data Index: 1198140 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0681. Min Act: -0.0006

Data Index: 288049 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0648. Min Act: -0.0006

Data Index: 990133 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0649. Min Act: -0.0006

Data Index: 1222459 (C4 (Web Text))

Max Activating Token Index: 543

Text #13

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0661. Min Act: -0.0006

Data Index: 1135722 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0593. Min Act: -0.0006

Data Index: 707164 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0686. Min Act: -0.0006

Data Index: 745867 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0622. Min Act: -0.0006

Data Index: 805751 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0633. Min Act: -0.0006

Data Index: 1056400 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0640. Min Act: -0.0006

Data Index: 64626 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.1037. Min Range: -0.1037

Max Act: 0.0638. Min Act: -0.0006

Data Index: 1302664 (C4 (Web Text))

Max Activating Token Index: 771