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

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

Neuron 3009 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4733. Min Range: -3.4733

Max Act: 3.4733. Min Act: -0.0000

Data Index: 652090 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 3.4733. Min Range: -3.4733

Max Act: 3.4018. Min Act: -0.0000

Data Index: 1197014 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 3.4733. Min Range: -3.4733

Max Act: 3.2958. Min Act: -0.0000

Data Index: 931207 (C4 (Web Text))

Max Activating Token Index: 626

Text #3

Max Range: 3.4733. Min Range: -3.4733

Max Act: 3.3193. Min Act: -0.0000

Data Index: 315617 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 3.4733. Min Range: -3.4733

Max Act: 3.2980. Min Act: -0.0000

Data Index: 650168 (C4 (Web Text))

Max Activating Token Index: 420

Text #5

Max Range: 3.4733. Min Range: -3.4733

Max Act: 3.1061. Min Act: -0.0000

Data Index: 320358 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 3.4733. Min Range: -3.4733

Max Act: 2.9267. Min Act: -0.0000

Data Index: 134094 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 3.4733. Min Range: -3.4733

Max Act: 3.0625. Min Act: -0.0000

Data Index: 1590505 (Python Code)

Max Activating Token Index: 479

Text #8

Max Range: 3.4733. Min Range: -3.4733

Max Act: 2.9920. Min Act: -0.0000

Data Index: 1227401 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 3.4733. Min Range: -3.4733

Max Act: 2.8856. Min Act: -0.0000

Data Index: 658882 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 3.4733. Min Range: -3.4733

Max Act: 2.8922. Min Act: -0.0000

Data Index: 493482 (C4 (Web Text))

Max Activating Token Index: 939

Text #11

Max Range: 3.4733. Min Range: -3.4733

Max Act: 2.6371. Min Act: -0.0000

Data Index: 543947 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 3.4733. Min Range: -3.4733

Max Act: 2.7264. Min Act: -0.0000

Data Index: 389649 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 3.4733. Min Range: -3.4733

Max Act: 2.7176. Min Act: -0.0000

Data Index: 905719 (C4 (Web Text))

Max Activating Token Index: 223

Text #14

Max Range: 3.4733. Min Range: -3.4733

Max Act: 2.5448. Min Act: -0.0000

Data Index: 948816 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 3.4733. Min Range: -3.4733

Max Act: 2.6853. Min Act: -0.0000

Data Index: 1436352 (Python Code)

Max Activating Token Index: 808

Text #16

Max Range: 3.4733. Min Range: -3.4733

Max Act: 2.6579. Min Act: -0.0000

Data Index: 1169886 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 3.4733. Min Range: -3.4733

Max Act: 2.5864. Min Act: -0.0000

Data Index: 1308910 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 3.4733. Min Range: -3.4733

Max Act: 2.4616. Min Act: -0.0000

Data Index: 368614 (C4 (Web Text))

Max Activating Token Index: 384

Text #19

Max Range: 3.4733. Min Range: -3.4733

Max Act: 2.4613. Min Act: -0.0000

Data Index: 108780 (C4 (Web Text))

Max Activating Token Index: 222