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

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

Neuron 3406 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1937. Min Act: -0.0000

Data Index: 1598711 (Python Code)

Max Activating Token Index: 155

Text #1

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1653334 (Python Code)

Max Activating Token Index: 46

Text #2

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1408492 (Python Code)

Max Activating Token Index: 116

Text #3

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1564. Min Act: -0.0000

Data Index: 1625584 (Python Code)

Max Activating Token Index: 473

Text #4

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1531297 (Python Code)

Max Activating Token Index: 14

Text #5

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1581502 (Python Code)

Max Activating Token Index: 23

Text #6

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1635. Min Act: -0.0000

Data Index: 1370088 (Python Code)

Max Activating Token Index: 98

Text #7

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1787. Min Act: -0.0000

Data Index: 1592817 (Python Code)

Max Activating Token Index: 152

Text #8

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1542520 (Python Code)

Max Activating Token Index: 23

Text #9

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1582. Min Act: -0.0000

Data Index: 1536553 (Python Code)

Max Activating Token Index: 327

Text #10

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1603. Min Act: -0.0000

Data Index: 1656260 (Python Code)

Max Activating Token Index: 20

Text #11

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1445. Min Act: -0.0000

Data Index: 1636221 (Python Code)

Max Activating Token Index: 210

Text #12

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1538. Min Act: -0.0000

Data Index: 1632045 (Python Code)

Max Activating Token Index: 23

Text #13

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1480. Min Act: -0.0000

Data Index: 1511745 (Python Code)

Max Activating Token Index: 16

Text #14

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1437. Min Act: -0.0000

Data Index: 1611792 (Python Code)

Max Activating Token Index: 196

Text #15

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1543. Min Act: -0.0000

Data Index: 1657081 (Python Code)

Max Activating Token Index: 10

Text #16

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1550. Min Act: -0.0000

Data Index: 1449621 (Python Code)

Max Activating Token Index: 436

Text #17

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1429. Min Act: -0.0000

Data Index: 1499961 (Python Code)

Max Activating Token Index: 376

Text #18

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1534. Min Act: -0.0000

Data Index: 1552255 (Python Code)

Max Activating Token Index: 410

Text #19

Max Range: 0.1937. Min Range: -0.1937

Max Act: 0.1355. Min Act: -0.0000

Data Index: 117550 (C4 (Web Text))

Max Activating Token Index: 159