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

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

Neuron 2735 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: 3.4879. Min Range: -3.4879

Max Act: 3.4879. Min Act: -0.0000

Data Index: 1560921 (Python Code)

Max Activating Token Index: 311

Text #1

Max Range: 3.4879. Min Range: -3.4879

Max Act: 3.0338. Min Act: -0.0000

Data Index: 923742 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 3.4879. Min Range: -3.4879

Max Act: 3.0465. Min Act: -0.0000

Data Index: 133300 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 3.4879. Min Range: -3.4879

Max Act: 3.2830. Min Act: -0.0000

Data Index: 764660 (C4 (Web Text))

Max Activating Token Index: 849

Text #4

Max Range: 3.4879. Min Range: -3.4879

Max Act: 2.9764. Min Act: -0.0000

Data Index: 1080329 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 3.4879. Min Range: -3.4879

Max Act: 2.8886. Min Act: 0.0000

Data Index: 1510997 (Python Code)

Max Activating Token Index: 691

Text #6

Max Range: 3.4879. Min Range: -3.4879

Max Act: 2.7072. Min Act: -0.0000

Data Index: 92567 (C4 (Web Text))

Max Activating Token Index: 521

Text #7

Max Range: 3.4879. Min Range: -3.4879

Max Act: 2.6371. Min Act: -0.0000

Data Index: 466263 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 3.4879. Min Range: -3.4879

Max Act: 2.7660. Min Act: -0.0000

Data Index: 13819 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 3.4879. Min Range: -3.4879

Max Act: 2.4711. Min Act: -0.0000

Data Index: 1298930 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 3.4879. Min Range: -3.4879

Max Act: 2.4344. Min Act: -0.0000

Data Index: 147205 (C4 (Web Text))

Max Activating Token Index: 955

Text #11

Max Range: 3.4879. Min Range: -3.4879

Max Act: 2.4425. Min Act: -0.0000

Data Index: 531645 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 3.4879. Min Range: -3.4879

Max Act: 2.5340. Min Act: -0.0000

Data Index: 257666 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 3.4879. Min Range: -3.4879

Max Act: 2.3524. Min Act: -0.0000

Data Index: 39723 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 3.4879. Min Range: -3.4879

Max Act: 2.3602. Min Act: -0.0000

Data Index: 674643 (C4 (Web Text))

Max Activating Token Index: 399

Text #15

Max Range: 3.4879. Min Range: -3.4879

Max Act: 2.3243. Min Act: 0.0001

Data Index: 1384655 (Python Code)

Max Activating Token Index: 76

Text #16

Max Range: 3.4879. Min Range: -3.4879

Max Act: 2.4579. Min Act: 0.0000

Data Index: 1151576 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 3.4879. Min Range: -3.4879

Max Act: 2.4302. Min Act: -0.0000

Data Index: 261716 (C4 (Web Text))

Max Activating Token Index: 462

Text #18

Max Range: 3.4879. Min Range: -3.4879

Max Act: 2.1317. Min Act: 0.0000

Data Index: 1362212 (Python Code)

Max Activating Token Index: 599

Text #19

Max Range: 3.4879. Min Range: -3.4879

Max Act: 2.3903. Min Act: -0.0000

Data Index: 53533 (C4 (Web Text))

Max Activating Token Index: 137