Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 95 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0550. Min Act: -0.0003

Data Index: 1139854 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0501. Min Act: -0.0003

Data Index: 1299286 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0492. Min Act: -0.0003

Data Index: 488623 (C4 (Web Text))

Max Activating Token Index: 863

Text #3

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0479. Min Act: -0.0003

Data Index: 150090 (C4 (Web Text))

Max Activating Token Index: 818

Text #4

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0449. Min Act: -0.0003

Data Index: 359872 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0452. Min Act: -0.0003

Data Index: 78417 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0458. Min Act: -0.0003

Data Index: 893729 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0449. Min Act: -0.0003

Data Index: 85997 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0451. Min Act: -0.0003

Data Index: 1083805 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0458. Min Act: -0.0003

Data Index: 168583 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0441. Min Act: -0.0003

Data Index: 752609 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0447. Min Act: -0.0003

Data Index: 445135 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0463. Min Act: -0.0003

Data Index: 259387 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0437. Min Act: -0.0003

Data Index: 1341049 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0387. Min Act: -0.0003

Data Index: 445585 (C4 (Web Text))

Max Activating Token Index: 588

Text #15

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0436. Min Act: -0.0003

Data Index: 1071714 (C4 (Web Text))

Max Activating Token Index: 185

Text #16

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0411. Min Act: -0.0003

Data Index: 1380151 (Python Code)

Max Activating Token Index: 283

Text #17

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0434. Min Act: -0.0003

Data Index: 675088 (C4 (Web Text))

Max Activating Token Index: 151

Text #18

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0386. Min Act: -0.0003

Data Index: 1244758 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0408. Min Act: -0.0003

Data Index: 877343 (C4 (Web Text))

Max Activating Token Index: 900