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

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

Neuron 533 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.2256. Min Act: -0.0001

Data Index: 729008 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1970. Min Act: -0.0001

Data Index: 1145204 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.2113. Min Act: -0.0001

Data Index: 485499 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.2023. Min Act: -0.0001

Data Index: 940908 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1798. Min Act: -0.0001

Data Index: 966395 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1943. Min Act: -0.0001

Data Index: 893366 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1925. Min Act: -0.0001

Data Index: 1067888 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1794. Min Act: -0.0001

Data Index: 722116 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1835. Min Act: -0.0001

Data Index: 1191871 (C4 (Web Text))

Max Activating Token Index: 488

Text #9

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1754. Min Act: -0.0001

Data Index: 232101 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1819. Min Act: -0.0001

Data Index: 652035 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1737. Min Act: -0.0001

Data Index: 75201 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1930. Min Act: -0.0001

Data Index: 196310 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1719. Min Act: -0.0001

Data Index: 1308024 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1777. Min Act: -0.0001

Data Index: 459518 (C4 (Web Text))

Max Activating Token Index: 821

Text #15

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1759. Min Act: -0.0001

Data Index: 879737 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1869. Min Act: -0.0001

Data Index: 103874 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1745. Min Act: -0.0001

Data Index: 285680 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1680. Min Act: -0.0001

Data Index: 922511 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.2256. Min Range: -0.2256

Max Act: 0.1668. Min Act: -0.0001

Data Index: 1107209 (C4 (Web Text))

Max Activating Token Index: 725