Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1210 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0516. Min Act: -0.0005

Data Index: 1587885 (Python Code)

Max Activating Token Index: 34

Text #1

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0446. Min Act: -0.0005

Data Index: 1404072 (Python Code)

Max Activating Token Index: 52

Text #2

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0424. Min Act: -0.0005

Data Index: 1541928 (Python Code)

Max Activating Token Index: 454

Text #3

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0407. Min Act: -0.0005

Data Index: 1637881 (Python Code)

Max Activating Token Index: 833

Text #4

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0399. Min Act: -0.0005

Data Index: 1620129 (Python Code)

Max Activating Token Index: 14

Text #5

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0399. Min Act: -0.0005

Data Index: 1496901 (Python Code)

Max Activating Token Index: 14

Text #6

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0406. Min Act: -0.0005

Data Index: 1620731 (Python Code)

Max Activating Token Index: 563

Text #7

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0398. Min Act: -0.0005

Data Index: 1563120 (Python Code)

Max Activating Token Index: 546

Text #8

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0396. Min Act: -0.0005

Data Index: 1610147 (Python Code)

Max Activating Token Index: 52

Text #9

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0405. Min Act: -0.0005

Data Index: 1542300 (Python Code)

Max Activating Token Index: 52

Text #10

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0377. Min Act: -0.0005

Data Index: 1544024 (Python Code)

Max Activating Token Index: 59

Text #11

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0401. Min Act: -0.0005

Data Index: 1591294 (Python Code)

Max Activating Token Index: 304

Text #12

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0389. Min Act: -0.0005

Data Index: 1622527 (Python Code)

Max Activating Token Index: 908

Text #13

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0380. Min Act: -0.0005

Data Index: 1568114 (Python Code)

Max Activating Token Index: 487

Text #14

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0388. Min Act: -0.0005

Data Index: 1417363 (Python Code)

Max Activating Token Index: 448

Text #15

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0379. Min Act: -0.0005

Data Index: 1376484 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0401. Min Act: -0.0005

Data Index: 1637370 (Python Code)

Max Activating Token Index: 699

Text #17

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0384. Min Act: -0.0005

Data Index: 1527820 (Python Code)

Max Activating Token Index: 27

Text #18

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0376. Min Act: -0.0005

Data Index: 1634374 (Python Code)

Max Activating Token Index: 29

Text #19

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0389. Min Act: -0.0005

Data Index: 1435627 (Python Code)

Max Activating Token Index: 257