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

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

Neuron 1275 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.4382. Min Act: -0.0002

Data Index: 1633588 (Python Code)

Max Activating Token Index: 532

Text #1

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.3783. Min Act: -0.0002

Data Index: 1592536 (Python Code)

Max Activating Token Index: 457

Text #2

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.2935. Min Act: -0.0002

Data Index: 1656976 (Python Code)

Max Activating Token Index: 421

Text #3

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.2906. Min Act: -0.0002

Data Index: 1621287 (Python Code)

Max Activating Token Index: 344

Text #4

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.2127. Min Act: -0.0002

Data Index: 1447384 (Python Code)

Max Activating Token Index: 988

Text #5

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.2571. Min Act: -0.0002

Data Index: 1544608 (Python Code)

Max Activating Token Index: 294

Text #6

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.2708. Min Act: -0.0002

Data Index: 1464211 (Python Code)

Max Activating Token Index: 890

Text #7

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.1864. Min Act: -0.0002

Data Index: 1512316 (Python Code)

Max Activating Token Index: 854

Text #8

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.1888. Min Act: -0.0002

Data Index: 1596681 (Python Code)

Max Activating Token Index: 916

Text #9

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.2821. Min Act: -0.0002

Data Index: 1578096 (Python Code)

Max Activating Token Index: 6

Text #10

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.2000. Min Act: -0.0002

Data Index: 1638899 (Python Code)

Max Activating Token Index: 423

Text #11

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.2055. Min Act: -0.0002

Data Index: 1437310 (Python Code)

Max Activating Token Index: 159

Text #12

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.2513. Min Act: -0.0002

Data Index: 1435472 (Python Code)

Max Activating Token Index: 12

Text #13

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.1738. Min Act: -0.0002

Data Index: 1482659 (Python Code)

Max Activating Token Index: 383

Text #14

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.0994. Min Act: -0.0002

Data Index: 1363890 (Python Code)

Max Activating Token Index: 157

Text #15

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.0973. Min Act: -0.0002

Data Index: 1370974 (Python Code)

Max Activating Token Index: 671

Text #16

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.2236. Min Act: -0.0002

Data Index: 1628613 (Python Code)

Max Activating Token Index: 433

Text #17

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.1233. Min Act: -0.0002

Data Index: 1390793 (Python Code)

Max Activating Token Index: 378

Text #18

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.1843. Min Act: -0.0002

Data Index: 1399526 (Python Code)

Max Activating Token Index: 430

Text #19

Max Range: 1.4382. Min Range: -1.4382

Max Act: 1.2293. Min Act: -0.0002

Data Index: 1492469 (Python Code)

Max Activating Token Index: 182