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

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

Neuron 4751 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2557. Min Range: -1.2557

Max Act: 1.2557. Min Act: -0.0000

Data Index: 1646642 (Python Code)

Max Activating Token Index: 98

Text #1

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.9210. Min Act: -0.0000

Data Index: 1451174 (Python Code)

Max Activating Token Index: 524

Text #2

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.8176. Min Act: -0.0000

Data Index: 1398674 (Python Code)

Max Activating Token Index: 783

Text #3

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.7157. Min Act: -0.0000

Data Index: 1557084 (Python Code)

Max Activating Token Index: 761

Text #4

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.7066. Min Act: -0.0000

Data Index: 1550635 (Python Code)

Max Activating Token Index: 434

Text #5

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1545236 (Python Code)

Max Activating Token Index: 349

Text #6

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.6257. Min Act: -0.0000

Data Index: 1538982 (Python Code)

Max Activating Token Index: 724

Text #7

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.6518. Min Act: -0.0000

Data Index: 1648441 (Python Code)

Max Activating Token Index: 586

Text #8

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.6639. Min Act: -0.0000

Data Index: 1571971 (Python Code)

Max Activating Token Index: 172

Text #9

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1655443 (Python Code)

Max Activating Token Index: 47

Text #10

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.6067. Min Act: -0.0000

Data Index: 1586041 (Python Code)

Max Activating Token Index: 1019

Text #11

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1598000 (Python Code)

Max Activating Token Index: 641

Text #12

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.6014. Min Act: -0.0000

Data Index: 1496568 (Python Code)

Max Activating Token Index: 140

Text #13

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.6045. Min Act: -0.0000

Data Index: 1481240 (Python Code)

Max Activating Token Index: 926

Text #14

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1423006 (Python Code)

Max Activating Token Index: 148

Text #15

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.6010. Min Act: -0.0000

Data Index: 1620771 (Python Code)

Max Activating Token Index: 256

Text #16

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.5849. Min Act: -0.0000

Data Index: 1483371 (Python Code)

Max Activating Token Index: 829

Text #17

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.5511. Min Act: -0.0000

Data Index: 1628609 (Python Code)

Max Activating Token Index: 968

Text #18

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.5345. Min Act: -0.0000

Data Index: 1516504 (Python Code)

Max Activating Token Index: 332

Text #19

Max Range: 1.2557. Min Range: -1.2557

Max Act: 0.6032. Min Act: -0.0000

Data Index: 1437701 (Python Code)

Max Activating Token Index: 683