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

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

Neuron 3129 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: 1.2382. Min Range: -1.2382

Max Act: 1.2382. Min Act: -0.0002

Data Index: 1468586 (Python Code)

Max Activating Token Index: 841

Text #1

Max Range: 1.2382. Min Range: -1.2382

Max Act: 1.1781. Min Act: -0.0002

Data Index: 1422627 (Python Code)

Max Activating Token Index: 437

Text #2

Max Range: 1.2382. Min Range: -1.2382

Max Act: 1.1643. Min Act: -0.0002

Data Index: 1550409 (Python Code)

Max Activating Token Index: 12

Text #3

Max Range: 1.2382. Min Range: -1.2382

Max Act: 1.0700. Min Act: -0.0002

Data Index: 1518403 (Python Code)

Max Activating Token Index: 486

Text #4

Max Range: 1.2382. Min Range: -1.2382

Max Act: 1.1211. Min Act: -0.0002

Data Index: 1419372 (Python Code)

Max Activating Token Index: 54

Text #5

Max Range: 1.2382. Min Range: -1.2382

Max Act: 1.0070. Min Act: -0.0002

Data Index: 1558255 (Python Code)

Max Activating Token Index: 365

Text #6

Max Range: 1.2382. Min Range: -1.2382

Max Act: 1.0015. Min Act: -0.0002

Data Index: 1628146 (Python Code)

Max Activating Token Index: 24

Text #7

Max Range: 1.2382. Min Range: -1.2382

Max Act: 0.9793. Min Act: -0.0002

Data Index: 1424538 (Python Code)

Max Activating Token Index: 831

Text #8

Max Range: 1.2382. Min Range: -1.2382

Max Act: 0.9721. Min Act: -0.0002

Data Index: 1431380 (Python Code)

Max Activating Token Index: 960

Text #9

Max Range: 1.2382. Min Range: -1.2382

Max Act: 0.9882. Min Act: -0.0002

Data Index: 1369761 (Python Code)

Max Activating Token Index: 376

Text #10

Max Range: 1.2382. Min Range: -1.2382

Max Act: 0.9837. Min Act: -0.0002

Data Index: 1377468 (Python Code)

Max Activating Token Index: 459

Text #11

Max Range: 1.2382. Min Range: -1.2382

Max Act: 0.9744. Min Act: -0.0002

Data Index: 1457964 (Python Code)

Max Activating Token Index: 242

Text #12

Max Range: 1.2382. Min Range: -1.2382

Max Act: 1.0362. Min Act: -0.0002

Data Index: 1634828 (Python Code)

Max Activating Token Index: 688

Text #13

Max Range: 1.2382. Min Range: -1.2382

Max Act: 0.9767. Min Act: -0.0002

Data Index: 1444700 (Python Code)

Max Activating Token Index: 920

Text #14

Max Range: 1.2382. Min Range: -1.2382

Max Act: 0.9268. Min Act: -0.0002

Data Index: 1403095 (Python Code)

Max Activating Token Index: 771

Text #15

Max Range: 1.2382. Min Range: -1.2382

Max Act: 1.0158. Min Act: -0.0002

Data Index: 1600115 (Python Code)

Max Activating Token Index: 734

Text #16

Max Range: 1.2382. Min Range: -1.2382

Max Act: 0.9226. Min Act: -0.0002

Data Index: 1462541 (Python Code)

Max Activating Token Index: 880

Text #17

Max Range: 1.2382. Min Range: -1.2382

Max Act: 0.9358. Min Act: -0.0002

Data Index: 1520266 (Python Code)

Max Activating Token Index: 858

Text #18

Max Range: 1.2382. Min Range: -1.2382

Max Act: 1.1260. Min Act: -0.0002

Data Index: 1407507 (Python Code)

Max Activating Token Index: 815

Text #19

Max Range: 1.2382. Min Range: -1.2382

Max Act: 1.0461. Min Act: -0.0002

Data Index: 1621289 (Python Code)

Max Activating Token Index: 773