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

Dataset: The Pile

Neuron 1871 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2756. Min Act: -0.0000

Data Index: 451237 (The Pile)

Max Activating Token Index: 128

Text #1

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2308. Min Act: -0.0000

Data Index: 1234960 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2294. Min Act: -0.0000

Data Index: 571221 (The Pile)

Max Activating Token Index: 542

Text #3

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2211. Min Act: -0.0000

Data Index: 953476 (The Pile)

Max Activating Token Index: 983

Text #4

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2385. Min Act: -0.0000

Data Index: 1404210 (The Pile)

Max Activating Token Index: 728

Text #5

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.1923. Min Act: -0.0000

Data Index: 858094 (The Pile)

Max Activating Token Index: 132

Text #6

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2073. Min Act: -0.0000

Data Index: 619708 (The Pile)

Max Activating Token Index: 291

Text #7

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.2034. Min Act: -0.0000

Data Index: 439458 (The Pile)

Max Activating Token Index: 531

Text #8

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.1768. Min Act: -0.0001

Data Index: 1549067 (The Pile)

Max Activating Token Index: 670

Text #9

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.1837. Min Act: -0.0000

Data Index: 1968405 (The Pile)

Max Activating Token Index: 367

Text #10

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.1961. Min Act: -0.0000

Data Index: 691742 (The Pile)

Max Activating Token Index: 463

Text #11

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1702507 (The Pile)

Max Activating Token Index: 203

Text #12

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.1904. Min Act: -0.0000

Data Index: 551841 (The Pile)

Max Activating Token Index: 337

Text #13

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.1798. Min Act: -0.0000

Data Index: 1225401 (The Pile)

Max Activating Token Index: 156

Text #14

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.1817. Min Act: -0.0000

Data Index: 351676 (The Pile)

Max Activating Token Index: 749

Text #15

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.1774. Min Act: -0.0000

Data Index: 1822461 (The Pile)

Max Activating Token Index: 388

Text #16

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.1744. Min Act: -0.0000

Data Index: 1558240 (The Pile)

Max Activating Token Index: 434

Text #17

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.1802. Min Act: -0.0000

Data Index: 1506535 (The Pile)

Max Activating Token Index: 207

Text #18

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.1735. Min Act: -0.0000

Data Index: 566152 (The Pile)

Max Activating Token Index: 143

Text #19

Max Range: 0.2756. Min Range: -0.2756

Max Act: 0.1763. Min Act: -0.0000

Data Index: 646017 (The Pile)

Max Activating Token Index: 132