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

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

Neuron 4686 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2372. Min Range: -2.2372

Max Act: 2.2372. Min Act: -0.0000

Data Index: 1156970 (C4 (Web Text))

Max Activating Token Index: 992

Text #1

Max Range: 2.2372. Min Range: -2.2372

Max Act: 2.0128. Min Act: -0.0000

Data Index: 848877 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.7618. Min Act: -0.0000

Data Index: 91059 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.7039. Min Act: -0.0000

Data Index: 475780 (C4 (Web Text))

Max Activating Token Index: 349

Text #4

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.5100. Min Act: -0.0000

Data Index: 936490 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.4476. Min Act: -0.0000

Data Index: 586124 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.4432. Min Act: -0.0000

Data Index: 859384 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.4466. Min Act: -0.0000

Data Index: 1215459 (C4 (Web Text))

Max Activating Token Index: 962

Text #8

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.3672. Min Act: -0.0000

Data Index: 390897 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.3586. Min Act: -0.0000

Data Index: 283150 (C4 (Web Text))

Max Activating Token Index: 194

Text #10

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.3408. Min Act: -0.0000

Data Index: 39207 (C4 (Web Text))

Max Activating Token Index: 240

Text #11

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.3403. Min Act: -0.0000

Data Index: 1231703 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.3282. Min Act: -0.0000

Data Index: 1301257 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.3197. Min Act: -0.0000

Data Index: 973694 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.3922. Min Act: -0.0000

Data Index: 1120677 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.3050. Min Act: -0.0000

Data Index: 921982 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.2090. Min Act: -0.0000

Data Index: 37445 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.1476. Min Act: -0.0000

Data Index: 618467 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.2331. Min Act: -0.0000

Data Index: 651584 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 2.2372. Min Range: -2.2372

Max Act: 1.2089. Min Act: -0.0000

Data Index: 1100162 (C4 (Web Text))

Max Activating Token Index: 616