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

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

Neuron 2900 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: 1.1706. Min Range: -1.1706

Max Act: 1.1052. Min Act: -0.0000

Data Index: 1490041 (Python Code)

Max Activating Token Index: 869

Text #1

Max Range: 1.1706. Min Range: -1.1706

Max Act: 1.0853. Min Act: -0.0000

Data Index: 1648161 (Python Code)

Max Activating Token Index: 702

Text #2

Max Range: 1.1706. Min Range: -1.1706

Max Act: 1.0257. Min Act: -0.0000

Data Index: 1552890 (Python Code)

Max Activating Token Index: 988

Text #3

Max Range: 1.1706. Min Range: -1.1706

Max Act: 1.0564. Min Act: -0.0000

Data Index: 1644928 (Python Code)

Max Activating Token Index: 812

Text #4

Max Range: 1.1706. Min Range: -1.1706

Max Act: 1.1706. Min Act: -0.0000

Data Index: 1497517 (Python Code)

Max Activating Token Index: 678

Text #5

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.9544. Min Act: -0.0000

Data Index: 1471565 (Python Code)

Max Activating Token Index: 798

Text #6

Max Range: 1.1706. Min Range: -1.1706

Max Act: 1.1198. Min Act: -0.0000

Data Index: 1030953 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 1.1706. Min Range: -1.1706

Max Act: 1.0971. Min Act: -0.0000

Data Index: 1100695 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 1.1706. Min Range: -1.1706

Max Act: 1.0358. Min Act: -0.0000

Data Index: 1501157 (Python Code)

Max Activating Token Index: 793

Text #9

Max Range: 1.1706. Min Range: -1.1706

Max Act: 1.0645. Min Act: -0.0000

Data Index: 1384559 (Python Code)

Max Activating Token Index: 600

Text #10

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.9985. Min Act: -0.0000

Data Index: 755579 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 1.1706. Min Range: -1.1706

Max Act: 1.0501. Min Act: -0.0000

Data Index: 1569691 (Python Code)

Max Activating Token Index: 310

Text #12

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.9324. Min Act: -0.0000

Data Index: 1424097 (Python Code)

Max Activating Token Index: 484

Text #13

Max Range: 1.1706. Min Range: -1.1706

Max Act: 1.0274. Min Act: -0.0000

Data Index: 1579468 (Python Code)

Max Activating Token Index: 663

Text #14

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.9755. Min Act: -0.0000

Data Index: 912397 (C4 (Web Text))

Max Activating Token Index: 568

Text #15

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.9070. Min Act: -0.0000

Data Index: 1401158 (Python Code)

Max Activating Token Index: 1003

Text #16

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.9023. Min Act: -0.0000

Data Index: 1502160 (Python Code)

Max Activating Token Index: 473

Text #17

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.9212. Min Act: -0.0000

Data Index: 122074 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.9254. Min Act: -0.0000

Data Index: 1102548 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 1.1706. Min Range: -1.1706

Max Act: 0.9137. Min Act: -0.0000

Data Index: 664266 (C4 (Web Text))

Max Activating Token Index: 483