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

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

Neuron 1579 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.8873. Min Act: -0.0000

Data Index: 1362947 (Python Code)

Max Activating Token Index: 599

Text #1

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.5327. Min Act: -0.0000

Data Index: 1452135 (Python Code)

Max Activating Token Index: 726

Text #2

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.3768. Min Act: -0.0000

Data Index: 1404578 (Python Code)

Max Activating Token Index: 660

Text #3

Max Range: 2.8873. Min Range: -2.8873

Max Act: 1.9821. Min Act: -0.0000

Data Index: 1575719 (Python Code)

Max Activating Token Index: 866

Text #4

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.2002. Min Act: -0.0000

Data Index: 1649500 (Python Code)

Max Activating Token Index: 1004

Text #5

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.1846. Min Act: -0.0000

Data Index: 1547104 (Python Code)

Max Activating Token Index: 649

Text #6

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.0464. Min Act: -0.0000

Data Index: 1604811 (Python Code)

Max Activating Token Index: 993

Text #7

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.1555. Min Act: -0.0000

Data Index: 1420647 (Python Code)

Max Activating Token Index: 44

Text #8

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.1241. Min Act: -0.0000

Data Index: 1597468 (Python Code)

Max Activating Token Index: 848

Text #9

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.0944. Min Act: -0.0000

Data Index: 1418180 (Python Code)

Max Activating Token Index: 166

Text #10

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.1211. Min Act: 0.0000

Data Index: 1560914 (Python Code)

Max Activating Token Index: 85

Text #11

Max Range: 2.8873. Min Range: -2.8873

Max Act: 1.9809. Min Act: -0.0000

Data Index: 1564058 (Python Code)

Max Activating Token Index: 733

Text #12

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.2086. Min Act: -0.0000

Data Index: 1590340 (Python Code)

Max Activating Token Index: 889

Text #13

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.0667. Min Act: -0.0000

Data Index: 1405078 (Python Code)

Max Activating Token Index: 940

Text #14

Max Range: 2.8873. Min Range: -2.8873

Max Act: 1.9506. Min Act: -0.0000

Data Index: 1420188 (Python Code)

Max Activating Token Index: 689

Text #15

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.0444. Min Act: -0.0000

Data Index: 1550147 (Python Code)

Max Activating Token Index: 384

Text #16

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.0440. Min Act: -0.0000

Data Index: 1655066 (Python Code)

Max Activating Token Index: 654

Text #17

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.0330. Min Act: -0.0000

Data Index: 1556211 (Python Code)

Max Activating Token Index: 247

Text #18

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.0201. Min Act: -0.0000

Data Index: 1627641 (Python Code)

Max Activating Token Index: 842

Text #19

Max Range: 2.8873. Min Range: -2.8873

Max Act: 2.0144. Min Act: -0.0000

Data Index: 1649677 (Python Code)

Max Activating Token Index: 116