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

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

Neuron 5108 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.8778. Min Act: -0.0000

Data Index: 1375458 (Python Code)

Max Activating Token Index: 42

Text #1

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.8316. Min Act: -0.0000

Data Index: 1579951 (Python Code)

Max Activating Token Index: 65

Text #2

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.8262. Min Act: -0.0000

Data Index: 1454250 (Python Code)

Max Activating Token Index: 741

Text #3

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.8485. Min Act: -0.0000

Data Index: 1599429 (Python Code)

Max Activating Token Index: 610

Text #4

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.8398. Min Act: -0.0000

Data Index: 1634466 (Python Code)

Max Activating Token Index: 709

Text #5

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.8279. Min Act: -0.0000

Data Index: 1421094 (Python Code)

Max Activating Token Index: 575

Text #6

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.8008. Min Act: -0.0000

Data Index: 1376079 (Python Code)

Max Activating Token Index: 496

Text #7

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7462. Min Act: -0.0000

Data Index: 1383744 (Python Code)

Max Activating Token Index: 187

Text #8

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.8382. Min Act: -0.0000

Data Index: 1655724 (Python Code)

Max Activating Token Index: 843

Text #9

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7547. Min Act: -0.0000

Data Index: 1517641 (Python Code)

Max Activating Token Index: 317

Text #10

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7909. Min Act: -0.0000

Data Index: 1471442 (Python Code)

Max Activating Token Index: 704

Text #11

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7729. Min Act: -0.0000

Data Index: 1478412 (Python Code)

Max Activating Token Index: 825

Text #12

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7249. Min Act: -0.0000

Data Index: 1456611 (Python Code)

Max Activating Token Index: 817

Text #13

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7580. Min Act: -0.0000

Data Index: 1226845 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.6641. Min Act: -0.0000

Data Index: 1583321 (Python Code)

Max Activating Token Index: 254

Text #15

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.6866. Min Act: -0.0000

Data Index: 566015 (C4 (Web Text))

Max Activating Token Index: 977

Text #16

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7361. Min Act: -0.0000

Data Index: 1561144 (Python Code)

Max Activating Token Index: 212

Text #17

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7336. Min Act: -0.0000

Data Index: 1497342 (Python Code)

Max Activating Token Index: 490

Text #18

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7125. Min Act: -0.0000

Data Index: 1630105 (Python Code)

Max Activating Token Index: 392

Text #19

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.6902. Min Act: -0.0000

Data Index: 909300 (C4 (Web Text))

Max Activating Token Index: 930