Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4923 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.2906. Min Act: -0.0000

Data Index: 1100587 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.1983. Min Act: -0.0000

Data Index: 1289542 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.1965. Min Act: -0.0000

Data Index: 931178 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.1752. Min Act: -0.0000

Data Index: 951137 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1457751 (Python Code)

Max Activating Token Index: 902

Text #5

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.1841. Min Act: -0.0000

Data Index: 579569 (C4 (Web Text))

Max Activating Token Index: 884

Text #6

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.1813. Min Act: -0.0000

Data Index: 931515 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.1748. Min Act: -0.0000

Data Index: 665172 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.1592. Min Act: -0.0000

Data Index: 1594113 (Python Code)

Max Activating Token Index: 275

Text #9

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.1593. Min Act: -0.0000

Data Index: 1254571 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.1486. Min Act: -0.0000

Data Index: 727520 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.1498. Min Act: -0.0000

Data Index: 261078 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.1530. Min Act: -0.0000

Data Index: 816778 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.1365. Min Act: -0.0000

Data Index: 1542895 (Python Code)

Max Activating Token Index: 275

Text #14

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.1396. Min Act: -0.0000

Data Index: 515162 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.1348. Min Act: -0.0000

Data Index: 100452 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.1489. Min Act: -0.0000

Data Index: 952355 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.1154. Min Act: -0.0000

Data Index: 1556345 (Python Code)

Max Activating Token Index: 950

Text #18

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.1379. Min Act: -0.0000

Data Index: 943937 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 0.2906. Min Range: -0.2906

Max Act: 0.1392. Min Act: -0.0000

Data Index: 650729 (C4 (Web Text))

Max Activating Token Index: 193