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

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

Neuron 862 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6358. Min Range: -3.6358

Max Act: 3.6358. Min Act: -0.0000

Data Index: 1416511 (Python Code)

Max Activating Token Index: 800

Text #1

Max Range: 3.6358. Min Range: -3.6358

Max Act: 3.2282. Min Act: -0.0000

Data Index: 1595991 (Python Code)

Max Activating Token Index: 343

Text #2

Max Range: 3.6358. Min Range: -3.6358

Max Act: 3.0430. Min Act: -0.0000

Data Index: 1409489 (Python Code)

Max Activating Token Index: 729

Text #3

Max Range: 3.6358. Min Range: -3.6358

Max Act: 3.0620. Min Act: -0.0000

Data Index: 1476128 (Python Code)

Max Activating Token Index: 322

Text #4

Max Range: 3.6358. Min Range: -3.6358

Max Act: 3.0038. Min Act: 0.0000

Data Index: 1431782 (Python Code)

Max Activating Token Index: 305

Text #5

Max Range: 3.6358. Min Range: -3.6358

Max Act: 2.6462. Min Act: -0.0000

Data Index: 1545580 (Python Code)

Max Activating Token Index: 14

Text #6

Max Range: 3.6358. Min Range: -3.6358

Max Act: 2.7090. Min Act: 0.0000

Data Index: 1493943 (Python Code)

Max Activating Token Index: 917

Text #7

Max Range: 3.6358. Min Range: -3.6358

Max Act: 2.3790. Min Act: -0.0000

Data Index: 1417905 (Python Code)

Max Activating Token Index: 13

Text #8

Max Range: 3.6358. Min Range: -3.6358

Max Act: 2.3502. Min Act: -0.0000

Data Index: 1478544 (Python Code)

Max Activating Token Index: 202

Text #9

Max Range: 3.6358. Min Range: -3.6358

Max Act: 2.4243. Min Act: -0.0000

Data Index: 1477082 (Python Code)

Max Activating Token Index: 577

Text #10

Max Range: 3.6358. Min Range: -3.6358

Max Act: 2.2727. Min Act: -0.0000

Data Index: 1389025 (Python Code)

Max Activating Token Index: 627

Text #11

Max Range: 3.6358. Min Range: -3.6358

Max Act: 2.0822. Min Act: -0.0000

Data Index: 1407425 (Python Code)

Max Activating Token Index: 77

Text #12

Max Range: 3.6358. Min Range: -3.6358

Max Act: 2.4421. Min Act: -0.0000

Data Index: 1620842 (Python Code)

Max Activating Token Index: 27

Text #13

Max Range: 3.6358. Min Range: -3.6358

Max Act: 2.3341. Min Act: -0.0000

Data Index: 1375859 (Python Code)

Max Activating Token Index: 706

Text #14

Max Range: 3.6358. Min Range: -3.6358

Max Act: 2.1022. Min Act: -0.0000

Data Index: 1483972 (Python Code)

Max Activating Token Index: 47

Text #15

Max Range: 3.6358. Min Range: -3.6358

Max Act: 1.9666. Min Act: -0.0000

Data Index: 1537071 (Python Code)

Max Activating Token Index: 17

Text #16

Max Range: 3.6358. Min Range: -3.6358

Max Act: 2.0740. Min Act: -0.0000

Data Index: 1548601 (Python Code)

Max Activating Token Index: 551

Text #17

Max Range: 3.6358. Min Range: -3.6358

Max Act: 2.1411. Min Act: -0.0000

Data Index: 1510687 (Python Code)

Max Activating Token Index: 1008

Text #18

Max Range: 3.6358. Min Range: -3.6358

Max Act: 1.9788. Min Act: -0.0000

Data Index: 1523802 (Python Code)

Max Activating Token Index: 622

Text #19

Max Range: 3.6358. Min Range: -3.6358

Max Act: 1.9665. Min Act: -0.0000

Data Index: 1380199 (Python Code)

Max Activating Token Index: 321