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

Dataset: The Pile

Neuron 806 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.2290. Min Act: -0.0000

Data Index: 1602601 (The Pile)

Max Activating Token Index: 461

Text #1

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.2090. Min Act: -0.0000

Data Index: 912872 (The Pile)

Max Activating Token Index: 392

Text #2

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.2077. Min Act: -0.0000

Data Index: 1494027 (The Pile)

Max Activating Token Index: 690

Text #3

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1972273 (The Pile)

Max Activating Token Index: 196

Text #4

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.2033. Min Act: -0.0000

Data Index: 950037 (The Pile)

Max Activating Token Index: 190

Text #5

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1922. Min Act: -0.0000

Data Index: 263308 (The Pile)

Max Activating Token Index: 536

Text #6

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1964. Min Act: -0.0000

Data Index: 1109948 (The Pile)

Max Activating Token Index: 164

Text #7

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1382394 (The Pile)

Max Activating Token Index: 411

Text #8

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1784. Min Act: -0.0000

Data Index: 1527618 (The Pile)

Max Activating Token Index: 625

Text #9

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1953. Min Act: -0.0000

Data Index: 1568445 (The Pile)

Max Activating Token Index: 948

Text #10

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1812. Min Act: -0.0000

Data Index: 511865 (The Pile)

Max Activating Token Index: 863

Text #11

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1824. Min Act: -0.0000

Data Index: 397468 (The Pile)

Max Activating Token Index: 681

Text #12

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1877. Min Act: -0.0000

Data Index: 139405 (The Pile)

Max Activating Token Index: 214

Text #13

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1863. Min Act: -0.0000

Data Index: 1291061 (The Pile)

Max Activating Token Index: 880

Text #14

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1693. Min Act: -0.0000

Data Index: 1381296 (The Pile)

Max Activating Token Index: 565

Text #15

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1786. Min Act: -0.0000

Data Index: 798560 (The Pile)

Max Activating Token Index: 543

Text #16

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1684937 (The Pile)

Max Activating Token Index: 299

Text #17

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1832. Min Act: -0.0000

Data Index: 415446 (The Pile)

Max Activating Token Index: 535

Text #18

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1952. Min Act: -0.0000

Data Index: 1517514 (The Pile)

Max Activating Token Index: 476

Text #19

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1748. Min Act: -0.0000

Data Index: 1677858 (The Pile)

Max Activating Token Index: 55