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

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

Neuron 1829 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1315. Min Range: -1.1315

Max Act: 1.1315. Min Act: -0.0000

Data Index: 653702 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.9814. Min Act: -0.0000

Data Index: 1617488 (Python Code)

Max Activating Token Index: 212

Text #2

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.9848. Min Act: -0.0000

Data Index: 1597984 (Python Code)

Max Activating Token Index: 379

Text #3

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.9788. Min Act: -0.0000

Data Index: 1559157 (Python Code)

Max Activating Token Index: 572

Text #4

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8700. Min Act: -0.0000

Data Index: 1509755 (Python Code)

Max Activating Token Index: 64

Text #5

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8616. Min Act: -0.0000

Data Index: 1526870 (Python Code)

Max Activating Token Index: 953

Text #6

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8585. Min Act: -0.0000

Data Index: 1639377 (Python Code)

Max Activating Token Index: 492

Text #7

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8274. Min Act: -0.0000

Data Index: 1630650 (Python Code)

Max Activating Token Index: 718

Text #8

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8507. Min Act: -0.0000

Data Index: 1588293 (Python Code)

Max Activating Token Index: 647

Text #9

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8779. Min Act: -0.0000

Data Index: 1550625 (Python Code)

Max Activating Token Index: 151

Text #10

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8429. Min Act: -0.0000

Data Index: 1508296 (Python Code)

Max Activating Token Index: 692

Text #11

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8464. Min Act: -0.0000

Data Index: 1459958 (Python Code)

Max Activating Token Index: 337

Text #12

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8453. Min Act: -0.0000

Data Index: 1371742 (Python Code)

Max Activating Token Index: 539

Text #13

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8433. Min Act: -0.0000

Data Index: 1465268 (Python Code)

Max Activating Token Index: 202

Text #14

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1465020 (Python Code)

Max Activating Token Index: 782

Text #15

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8354. Min Act: -0.0000

Data Index: 1329645 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8394. Min Act: -0.0000

Data Index: 1613975 (Python Code)

Max Activating Token Index: 129

Text #17

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8785. Min Act: -0.0000

Data Index: 1228316 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8630. Min Act: -0.0000

Data Index: 1367264 (Python Code)

Max Activating Token Index: 988

Text #19

Max Range: 1.1315. Min Range: -1.1315

Max Act: 0.8053. Min Act: -0.0000

Data Index: 1554566 (Python Code)

Max Activating Token Index: 584