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

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

Neuron 5830 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9425. Min Range: -3.9425

Max Act: 3.9425. Min Act: -0.0000

Data Index: 1639078 (Python Code)

Max Activating Token Index: 736

Text #1

Max Range: 3.9425. Min Range: -3.9425

Max Act: 2.9564. Min Act: -0.0000

Data Index: 1510875 (Python Code)

Max Activating Token Index: 481

Text #2

Max Range: 3.9425. Min Range: -3.9425

Max Act: 3.0216. Min Act: -0.0000

Data Index: 1502523 (Python Code)

Max Activating Token Index: 272

Text #3

Max Range: 3.9425. Min Range: -3.9425

Max Act: 2.8556. Min Act: -0.0000

Data Index: 419239 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 3.9425. Min Range: -3.9425

Max Act: 2.7985. Min Act: -0.0000

Data Index: 1591301 (Python Code)

Max Activating Token Index: 312

Text #5

Max Range: 3.9425. Min Range: -3.9425

Max Act: 2.9038. Min Act: -0.0000

Data Index: 1538215 (Python Code)

Max Activating Token Index: 866

Text #6

Max Range: 3.9425. Min Range: -3.9425

Max Act: 2.6607. Min Act: -0.0000

Data Index: 1606614 (Python Code)

Max Activating Token Index: 576

Text #7

Max Range: 3.9425. Min Range: -3.9425

Max Act: 2.7184. Min Act: -0.0000

Data Index: 1637100 (Python Code)

Max Activating Token Index: 325

Text #8

Max Range: 3.9425. Min Range: -3.9425

Max Act: 2.4729. Min Act: -0.0000

Data Index: 1439357 (Python Code)

Max Activating Token Index: 882

Text #9

Max Range: 3.9425. Min Range: -3.9425

Max Act: 2.4655. Min Act: -0.0000

Data Index: 1647612 (Python Code)

Max Activating Token Index: 946

Text #10

Max Range: 3.9425. Min Range: -3.9425

Max Act: 2.4212. Min Act: -0.0000

Data Index: 1407314 (Python Code)

Max Activating Token Index: 279

Text #11

Max Range: 3.9425. Min Range: -3.9425

Max Act: 2.4602. Min Act: -0.0000

Data Index: 1626582 (Python Code)

Max Activating Token Index: 199

Text #12

Max Range: 3.9425. Min Range: -3.9425

Max Act: 2.3366. Min Act: -0.0000

Data Index: 1391555 (Python Code)

Max Activating Token Index: 981

Text #13

Max Range: 3.9425. Min Range: -3.9425

Max Act: 2.1915. Min Act: -0.0000

Data Index: 1525155 (Python Code)

Max Activating Token Index: 403

Text #14

Max Range: 3.9425. Min Range: -3.9425

Max Act: 2.2801. Min Act: -0.0000

Data Index: 1502548 (Python Code)

Max Activating Token Index: 74

Text #15

Max Range: 3.9425. Min Range: -3.9425

Max Act: 2.2205. Min Act: -0.0000

Data Index: 1365263 (Python Code)

Max Activating Token Index: 414

Text #16

Max Range: 3.9425. Min Range: -3.9425

Max Act: 2.1976. Min Act: -0.0000

Data Index: 1543139 (Python Code)

Max Activating Token Index: 650

Text #17

Max Range: 3.9425. Min Range: -3.9425

Max Act: 2.2916. Min Act: -0.0000

Data Index: 1614697 (Python Code)

Max Activating Token Index: 119

Text #18

Max Range: 3.9425. Min Range: -3.9425

Max Act: 2.1242. Min Act: -0.0000

Data Index: 1401330 (Python Code)

Max Activating Token Index: 709

Text #19

Max Range: 3.9425. Min Range: -3.9425

Max Act: 2.0989. Min Act: -0.0000

Data Index: 1365400 (Python Code)

Max Activating Token Index: 671