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

Dataset: The Pile

Neuron 1685 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2251. Min Act: -0.0000

Data Index: 103491 (The Pile)

Max Activating Token Index: 539

Text #1

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2525. Min Act: -0.0000

Data Index: 930839 (The Pile)

Max Activating Token Index: 953

Text #2

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2453. Min Act: -0.0000

Data Index: 1982959 (The Pile)

Max Activating Token Index: 198

Text #3

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2226. Min Act: -0.0000

Data Index: 384675 (The Pile)

Max Activating Token Index: 172

Text #4

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2437. Min Act: -0.0000

Data Index: 1819512 (The Pile)

Max Activating Token Index: 712

Text #5

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1893. Min Act: -0.0000

Data Index: 1351152 (The Pile)

Max Activating Token Index: 912

Text #6

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1966248 (The Pile)

Max Activating Token Index: 970

Text #7

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1054543 (The Pile)

Max Activating Token Index: 457

Text #8

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1822796 (The Pile)

Max Activating Token Index: 481

Text #9

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1905. Min Act: -0.0000

Data Index: 961195 (The Pile)

Max Activating Token Index: 1009

Text #10

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1887701 (The Pile)

Max Activating Token Index: 165

Text #11

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1964. Min Act: -0.0000

Data Index: 1752749 (The Pile)

Max Activating Token Index: 513

Text #12

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2091. Min Act: -0.0000

Data Index: 654614 (The Pile)

Max Activating Token Index: 83

Text #13

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1884. Min Act: -0.0000

Data Index: 879169 (The Pile)

Max Activating Token Index: 403

Text #14

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1856. Min Act: -0.0000

Data Index: 1555152 (The Pile)

Max Activating Token Index: 374

Text #15

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1759268 (The Pile)

Max Activating Token Index: 274

Text #16

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1953. Min Act: -0.0000

Data Index: 285653 (The Pile)

Max Activating Token Index: 215

Text #17

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1684. Min Act: -0.0000

Data Index: 1374330 (The Pile)

Max Activating Token Index: 107

Text #18

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1680. Min Act: -0.0000

Data Index: 701111 (The Pile)

Max Activating Token Index: 65

Text #19

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1733. Min Act: -0.0000

Data Index: 1806564 (The Pile)

Max Activating Token Index: 959