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

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

Neuron 592 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6182. Min Range: -1.6182

Max Act: 1.6182. Min Act: 0.0000

Data Index: 1504785 (Python Code)

Max Activating Token Index: 986

Text #1

Max Range: 1.6182. Min Range: -1.6182

Max Act: 1.4401. Min Act: 0.0000

Data Index: 1500067 (Python Code)

Max Activating Token Index: 948

Text #2

Max Range: 1.6182. Min Range: -1.6182

Max Act: 0.9576. Min Act: 0.0000

Data Index: 1609597 (Python Code)

Max Activating Token Index: 984

Text #3

Max Range: 1.6182. Min Range: -1.6182

Max Act: 0.9094. Min Act: -0.0000

Data Index: 1575481 (Python Code)

Max Activating Token Index: 942

Text #4

Max Range: 1.6182. Min Range: -1.6182

Max Act: 0.8548. Min Act: -0.0000

Data Index: 1399910 (Python Code)

Max Activating Token Index: 238

Text #5

Max Range: 1.6182. Min Range: -1.6182

Max Act: 0.8506. Min Act: 0.0000

Data Index: 1411476 (Python Code)

Max Activating Token Index: 769

Text #6

Max Range: 1.6182. Min Range: -1.6182

Max Act: 0.8736. Min Act: 0.0000

Data Index: 1427177 (Python Code)

Max Activating Token Index: 609

Text #7

Max Range: 1.6182. Min Range: -1.6182

Max Act: 0.8889. Min Act: -0.0000

Data Index: 1645039 (Python Code)

Max Activating Token Index: 611

Text #8

Max Range: 1.6182. Min Range: -1.6182

Max Act: 0.8806. Min Act: -0.0000

Data Index: 1590208 (Python Code)

Max Activating Token Index: 623

Text #9

Max Range: 1.6182. Min Range: -1.6182

Max Act: 0.8723. Min Act: -0.0000

Data Index: 1433301 (Python Code)

Max Activating Token Index: 1007

Text #10

Max Range: 1.6182. Min Range: -1.6182

Max Act: 0.8617. Min Act: -0.0000

Data Index: 1542367 (Python Code)

Max Activating Token Index: 784

Text #11

Max Range: 1.6182. Min Range: -1.6182

Max Act: 0.7904. Min Act: -0.0000

Data Index: 409812 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 1.6182. Min Range: -1.6182

Max Act: 0.9054. Min Act: -0.0000

Data Index: 386684 (C4 (Web Text))

Max Activating Token Index: 334

Text #13

Max Range: 1.6182. Min Range: -1.6182

Max Act: 0.7891. Min Act: -0.0000

Data Index: 1377948 (Python Code)

Max Activating Token Index: 283

Text #14

Max Range: 1.6182. Min Range: -1.6182

Max Act: 0.7848. Min Act: 0.0000

Data Index: 1537458 (Python Code)

Max Activating Token Index: 719

Text #15

Max Range: 1.6182. Min Range: -1.6182

Max Act: 0.8025. Min Act: 0.0000

Data Index: 1401373 (Python Code)

Max Activating Token Index: 44

Text #16

Max Range: 1.6182. Min Range: -1.6182

Max Act: 0.7338. Min Act: -0.0000

Data Index: 1367382 (Python Code)

Max Activating Token Index: 200

Text #17

Max Range: 1.6182. Min Range: -1.6182

Max Act: 0.8036. Min Act: -0.0000

Data Index: 1606957 (Python Code)

Max Activating Token Index: 506

Text #18

Max Range: 1.6182. Min Range: -1.6182

Max Act: 0.7487. Min Act: -0.0000

Data Index: 1361464 (Python Code)

Max Activating Token Index: 693

Text #19

Max Range: 1.6182. Min Range: -1.6182

Max Act: 0.7756. Min Act: -0.0000

Data Index: 1639646 (Python Code)

Max Activating Token Index: 180