Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2540 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.3850. Min Act: -0.0001

Data Index: 1412528 (Python Code)

Max Activating Token Index: 991

Text #1

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.3075. Min Act: -0.0001

Data Index: 1469039 (Python Code)

Max Activating Token Index: 568

Text #2

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.3984. Min Act: -0.0001

Data Index: 1561667 (Python Code)

Max Activating Token Index: 520

Text #3

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.2710. Min Act: -0.0001

Data Index: 1419274 (Python Code)

Max Activating Token Index: 441

Text #4

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.2190. Min Act: -0.0001

Data Index: 1458875 (Python Code)

Max Activating Token Index: 644

Text #5

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.3220. Min Act: -0.0001

Data Index: 1525961 (Python Code)

Max Activating Token Index: 368

Text #6

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.2674. Min Act: -0.0001

Data Index: 1462165 (Python Code)

Max Activating Token Index: 735

Text #7

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.2360. Min Act: -0.0001

Data Index: 1417448 (Python Code)

Max Activating Token Index: 623

Text #8

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.2346. Min Act: -0.0001

Data Index: 1435187 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.0905. Min Act: -0.0001

Data Index: 1500849 (Python Code)

Max Activating Token Index: 650

Text #10

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.2470. Min Act: -0.0001

Data Index: 1549550 (Python Code)

Max Activating Token Index: 664

Text #11

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.2759. Min Act: -0.0001

Data Index: 1400303 (Python Code)

Max Activating Token Index: 919

Text #12

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.2150. Min Act: -0.0001

Data Index: 1612303 (Python Code)

Max Activating Token Index: 466

Text #13

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.1671. Min Act: -0.0001

Data Index: 1507586 (Python Code)

Max Activating Token Index: 815

Text #14

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.1966. Min Act: -0.0001

Data Index: 1519890 (Python Code)

Max Activating Token Index: 142

Text #15

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.2004. Min Act: -0.0001

Data Index: 1360258 (Python Code)

Max Activating Token Index: 905

Text #16

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.1143. Min Act: -0.0001

Data Index: 1624826 (Python Code)

Max Activating Token Index: 606

Text #17

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.2558. Min Act: -0.0001

Data Index: 1563146 (Python Code)

Max Activating Token Index: 293

Text #18

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.1749. Min Act: -0.0001

Data Index: 1401806 (Python Code)

Max Activating Token Index: 987

Text #19

Max Range: 1.3984. Min Range: -1.3984

Max Act: 1.1731. Min Act: -0.0001

Data Index: 1435437 (Python Code)

Max Activating Token Index: 342