Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1001 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0561. Min Act: -0.0002

Data Index: 126968 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0491. Min Act: -0.0002

Data Index: 529454 (C4 (Web Text))

Max Activating Token Index: 790

Text #2

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0495. Min Act: -0.0002

Data Index: 558791 (C4 (Web Text))

Max Activating Token Index: 636

Text #3

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0465. Min Act: -0.0002

Data Index: 273876 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1090268 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0437. Min Act: -0.0002

Data Index: 367078 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0458. Min Act: -0.0002

Data Index: 92190 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0453. Min Act: -0.0002

Data Index: 613134 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0431. Min Act: -0.0002

Data Index: 715749 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0435. Min Act: -0.0002

Data Index: 771114 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0422. Min Act: -0.0002

Data Index: 143077 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1158862 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0408. Min Act: -0.0002

Data Index: 1311454 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0427. Min Act: -0.0002

Data Index: 837993 (C4 (Web Text))

Max Activating Token Index: 535

Text #14

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1169386 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0415. Min Act: -0.0002

Data Index: 22237 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1210004 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0408. Min Act: -0.0002

Data Index: 642168 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0398. Min Act: -0.0002

Data Index: 19613 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0407. Min Act: -0.0002

Data Index: 871977 (C4 (Web Text))

Max Activating Token Index: 885