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

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

Neuron 2382 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.2268. Min Act: -0.0001

Data Index: 75918 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.2084. Min Act: -0.0001

Data Index: 1314945 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.2152. Min Act: -0.0000

Data Index: 536370 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1930. Min Act: -0.0000

Data Index: 174578 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1922. Min Act: -0.0000

Data Index: 407081 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1812. Min Act: -0.0000

Data Index: 343100 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1866. Min Act: -0.0000

Data Index: 179531 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1925. Min Act: -0.0000

Data Index: 524414 (C4 (Web Text))

Max Activating Token Index: 834

Text #8

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1847. Min Act: -0.0000

Data Index: 1153431 (C4 (Web Text))

Max Activating Token Index: 523

Text #9

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1837. Min Act: -0.0000

Data Index: 124554 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1834. Min Act: -0.0000

Data Index: 164216 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1712. Min Act: -0.0000

Data Index: 265418 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1750. Min Act: -0.0000

Data Index: 575148 (C4 (Web Text))

Max Activating Token Index: 652

Text #13

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1684. Min Act: -0.0000

Data Index: 217194 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1796. Min Act: -0.0001

Data Index: 1013170 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1670. Min Act: -0.0000

Data Index: 958719 (C4 (Web Text))

Max Activating Token Index: 11

Text #16

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1711. Min Act: -0.0000

Data Index: 868367 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1646. Min Act: -0.0000

Data Index: 934902 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1694. Min Act: -0.0000

Data Index: 511675 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1671. Min Act: -0.0000

Data Index: 164248 (C4 (Web Text))

Max Activating Token Index: 75