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

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

Neuron 4968 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2628. Min Act: -0.0000

Data Index: 764297 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2345. Min Act: -0.0000

Data Index: 51165 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2094. Min Act: -0.0000

Data Index: 1274439 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2080. Min Act: -0.0000

Data Index: 862676 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1252649 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2068. Min Act: -0.0000

Data Index: 1359043 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1916. Min Act: -0.0000

Data Index: 1347281 (C4 (Web Text))

Max Activating Token Index: 68

Text #7

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1908. Min Act: -0.0000

Data Index: 983952 (C4 (Web Text))

Max Activating Token Index: 989

Text #8

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1246962 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1845. Min Act: -0.0000

Data Index: 621378 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1867. Min Act: -0.0000

Data Index: 348252 (C4 (Web Text))

Max Activating Token Index: 7

Text #11

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1860. Min Act: -0.0000

Data Index: 326924 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1807. Min Act: -0.0000

Data Index: 1420407 (Python Code)

Max Activating Token Index: 432

Text #13

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1793. Min Act: -0.0000

Data Index: 1128245 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1841. Min Act: -0.0000

Data Index: 264984 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1881. Min Act: -0.0000

Data Index: 381805 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1633. Min Act: -0.0000

Data Index: 383820 (C4 (Web Text))

Max Activating Token Index: 771

Text #17

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1799. Min Act: -0.0000

Data Index: 1499911 (Python Code)

Max Activating Token Index: 330

Text #18

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1935. Min Act: -0.0000

Data Index: 701127 (C4 (Web Text))

Max Activating Token Index: 1014

Text #19

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1779. Min Act: -0.0000

Data Index: 564064 (C4 (Web Text))

Max Activating Token Index: 921