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

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

Neuron 4420 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.3090. Min Act: -0.0000

Data Index: 1619658 (Python Code)

Max Activating Token Index: 978

Text #1

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2979. Min Act: -0.0001

Data Index: 1456554 (Python Code)

Max Activating Token Index: 343

Text #2

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2962. Min Act: -0.0000

Data Index: 1495226 (Python Code)

Max Activating Token Index: 52

Text #3

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2806. Min Act: -0.0001

Data Index: 1540461 (Python Code)

Max Activating Token Index: 381

Text #4

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2585. Min Act: -0.0001

Data Index: 1405491 (Python Code)

Max Activating Token Index: 528

Text #5

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2578. Min Act: -0.0001

Data Index: 1171706 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2291. Min Act: -0.0001

Data Index: 1654091 (Python Code)

Max Activating Token Index: 562

Text #7

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.2353. Min Act: -0.0000

Data Index: 1575896 (Python Code)

Max Activating Token Index: 134

Text #8

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.1889. Min Act: -0.0000

Data Index: 1427591 (Python Code)

Max Activating Token Index: 747

Text #9

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.1922. Min Act: -0.0001

Data Index: 1457445 (Python Code)

Max Activating Token Index: 454

Text #10

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.1774. Min Act: -0.0001

Data Index: 1604844 (Python Code)

Max Activating Token Index: 726

Text #11

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.1644. Min Act: -0.0000

Data Index: 1595363 (Python Code)

Max Activating Token Index: 207

Text #12

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.1606. Min Act: -0.0000

Data Index: 1549095 (Python Code)

Max Activating Token Index: 715

Text #13

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.1541. Min Act: -0.0000

Data Index: 636072 (C4 (Web Text))

Max Activating Token Index: 624

Text #14

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.1550. Min Act: -0.0000

Data Index: 756714 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.1513. Min Act: -0.0000

Data Index: 676088 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.1569. Min Act: -0.0001

Data Index: 1512062 (Python Code)

Max Activating Token Index: 913

Text #17

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.1655. Min Act: -0.0001

Data Index: 1386599 (Python Code)

Max Activating Token Index: 822

Text #18

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.1372. Min Act: -0.0000

Data Index: 1637749 (Python Code)

Max Activating Token Index: 393

Text #19

Max Range: 0.3090. Min Range: -0.3090

Max Act: 0.1460. Min Act: -0.0001

Data Index: 1044015 (C4 (Web Text))

Max Activating Token Index: 154