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

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

Neuron 1392 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.4439. Min Act: -0.0000

Data Index: 743411 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.4309. Min Act: -0.0000

Data Index: 1325071 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.4048. Min Act: -0.0000

Data Index: 940012 (C4 (Web Text))

Max Activating Token Index: 73

Text #3

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3966. Min Act: -0.0000

Data Index: 924825 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3504. Min Act: -0.0000

Data Index: 1515689 (Python Code)

Max Activating Token Index: 674

Text #5

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3546. Min Act: -0.0000

Data Index: 510861 (C4 (Web Text))

Max Activating Token Index: 844

Text #6

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3297. Min Act: -0.0001

Data Index: 1466788 (Python Code)

Max Activating Token Index: 275

Text #7

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3607. Min Act: -0.0000

Data Index: 321533 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3646. Min Act: -0.0000

Data Index: 1390602 (Python Code)

Max Activating Token Index: 264

Text #9

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3560. Min Act: -0.0000

Data Index: 696123 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3632. Min Act: -0.0000

Data Index: 708432 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3602. Min Act: -0.0000

Data Index: 663416 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3405. Min Act: -0.0000

Data Index: 1335291 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3197. Min Act: -0.0000

Data Index: 948533 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3490. Min Act: -0.0000

Data Index: 180047 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3399. Min Act: -0.0000

Data Index: 239143 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3283. Min Act: -0.0000

Data Index: 630137 (C4 (Web Text))

Max Activating Token Index: 301

Text #17

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3372. Min Act: -0.0000

Data Index: 776330 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3145. Min Act: -0.0000

Data Index: 1392024 (Python Code)

Max Activating Token Index: 734

Text #19

Max Range: 0.4439. Min Range: -0.4439

Max Act: 0.3223. Min Act: -0.0000

Data Index: 1492846 (Python Code)

Max Activating Token Index: 79