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

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

Neuron 4664 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2836. Min Range: -1.2836

Max Act: 1.2836. Min Act: -0.0001

Data Index: 123181 (C4 (Web Text))

Max Activating Token Index: 444

Text #1

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.8719. Min Act: -0.0001

Data Index: 461056 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.0083. Min Act: -0.0001

Data Index: 1214737 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.0594. Min Act: -0.0000

Data Index: 957451 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.0317. Min Act: -0.0000

Data Index: 652672 (C4 (Web Text))

Max Activating Token Index: 655

Text #5

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.0273. Min Act: -0.0000

Data Index: 324515 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.0280. Min Act: -0.0000

Data Index: 850668 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.0246. Min Act: -0.0000

Data Index: 514591 (C4 (Web Text))

Max Activating Token Index: 797

Text #8

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.0254. Min Act: -0.0001

Data Index: 1343006 (C4 (Web Text))

Max Activating Token Index: 17

Text #9

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.0267. Min Act: -0.0000

Data Index: 1503695 (Python Code)

Max Activating Token Index: 708

Text #10

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.0256. Min Act: -0.0000

Data Index: 362923 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.0147. Min Act: -0.0001

Data Index: 756103 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.0266. Min Act: -0.0000

Data Index: 118902 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.0244. Min Act: -0.0000

Data Index: 1302041 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.0146. Min Act: -0.0001

Data Index: 45343 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.0246. Min Act: -0.0000

Data Index: 1600266 (Python Code)

Max Activating Token Index: 195

Text #16

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.0243. Min Act: -0.0000

Data Index: 530610 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.0236. Min Act: -0.0001

Data Index: 82635 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.0239. Min Act: -0.0000

Data Index: 340153 (C4 (Web Text))

Max Activating Token Index: 941

Text #19

Max Range: 1.2836. Min Range: -1.2836

Max Act: 0.0248. Min Act: -0.0000

Data Index: 792543 (C4 (Web Text))

Max Activating Token Index: 7