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

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

Neuron 2124 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0650. Min Range: -1.0650

Max Act: 1.0650. Min Act: -0.0000

Data Index: 1141929 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 1.0650. Min Range: -1.0650

Max Act: 1.0251. Min Act: 0.0000

Data Index: 808246 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9966. Min Act: -0.0000

Data Index: 1147381 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9836. Min Act: 0.0000

Data Index: 708990 (C4 (Web Text))

Max Activating Token Index: 784

Text #4

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9695. Min Act: -0.0000

Data Index: 1122437 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9677. Min Act: -0.0000

Data Index: 626754 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9521. Min Act: -0.0000

Data Index: 537156 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9374. Min Act: -0.0000

Data Index: 546836 (C4 (Web Text))

Max Activating Token Index: 830

Text #8

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.9287. Min Act: -0.0000

Data Index: 58561 (C4 (Web Text))

Max Activating Token Index: 1003

Text #9

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8870. Min Act: -0.0000

Data Index: 525460 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8600. Min Act: -0.0000

Data Index: 592153 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8600. Min Act: -0.0000

Data Index: 219251 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8722. Min Act: -0.0000

Data Index: 1077306 (C4 (Web Text))

Max Activating Token Index: 559

Text #13

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8723. Min Act: -0.0000

Data Index: 1167321 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8647. Min Act: -0.0000

Data Index: 1039134 (C4 (Web Text))

Max Activating Token Index: 49

Text #15

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8338. Min Act: -0.0000

Data Index: 939960 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8256. Min Act: -0.0000

Data Index: 1238389 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8065. Min Act: -0.0000

Data Index: 424315 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8175. Min Act: -0.0000

Data Index: 611543 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 1.0650. Min Range: -1.0650

Max Act: 0.8180. Min Act: -0.0000

Data Index: 12915 (C4 (Web Text))

Max Activating Token Index: 812