Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 359 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1928. Min Act: -0.0003

Data Index: 1616396 (Python Code)

Max Activating Token Index: 57

Text #1

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1933. Min Act: -0.0003

Data Index: 840057 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1829. Min Act: -0.0003

Data Index: 319407 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1862. Min Act: -0.0003

Data Index: 1537477 (Python Code)

Max Activating Token Index: 965

Text #4

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1611. Min Act: -0.0003

Data Index: 438743 (C4 (Web Text))

Max Activating Token Index: 712

Text #5

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1460. Min Act: -0.0003

Data Index: 1653047 (Python Code)

Max Activating Token Index: 43

Text #6

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1490. Min Act: -0.0003

Data Index: 1628271 (Python Code)

Max Activating Token Index: 582

Text #7

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1459. Min Act: -0.0003

Data Index: 1386098 (Python Code)

Max Activating Token Index: 830

Text #8

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1459. Min Act: -0.0003

Data Index: 1432472 (Python Code)

Max Activating Token Index: 228

Text #9

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1485. Min Act: -0.0003

Data Index: 593067 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1456. Min Act: -0.0003

Data Index: 1404050 (Python Code)

Max Activating Token Index: 526

Text #11

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1444. Min Act: -0.0003

Data Index: 1028296 (C4 (Web Text))

Max Activating Token Index: 816

Text #12

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1459. Min Act: -0.0003

Data Index: 1074524 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1354. Min Act: -0.0003

Data Index: 592532 (C4 (Web Text))

Max Activating Token Index: 824

Text #14

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1346. Min Act: -0.0003

Data Index: 1556371 (Python Code)

Max Activating Token Index: 279

Text #15

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1457. Min Act: -0.0003

Data Index: 968371 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1366. Min Act: -0.0003

Data Index: 1474014 (Python Code)

Max Activating Token Index: 656

Text #17

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1385. Min Act: -0.0003

Data Index: 1514803 (Python Code)

Max Activating Token Index: 59

Text #18

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1415. Min Act: -0.0003

Data Index: 1405922 (Python Code)

Max Activating Token Index: 52

Text #19

Max Range: 0.1933. Min Range: -0.1933

Max Act: 0.1359. Min Act: -0.0004

Data Index: 1450822 (Python Code)

Max Activating Token Index: 908