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

Dataset: The Pile

Neuron 279 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.2276. Min Act: -0.0000

Data Index: 1671832 (The Pile)

Max Activating Token Index: 685

Text #1

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1985. Min Act: -0.0000

Data Index: 932480 (The Pile)

Max Activating Token Index: 335

Text #2

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.2008. Min Act: -0.0000

Data Index: 1259656 (The Pile)

Max Activating Token Index: 177

Text #3

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1968. Min Act: -0.0000

Data Index: 1173741 (The Pile)

Max Activating Token Index: 294

Text #4

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1897. Min Act: -0.0000

Data Index: 514155 (The Pile)

Max Activating Token Index: 450

Text #5

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1840. Min Act: -0.0000

Data Index: 1221084 (The Pile)

Max Activating Token Index: 894

Text #6

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1884. Min Act: -0.0000

Data Index: 1822927 (The Pile)

Max Activating Token Index: 103

Text #7

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1857. Min Act: -0.0000

Data Index: 741185 (The Pile)

Max Activating Token Index: 80

Text #8

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1975. Min Act: -0.0000

Data Index: 761356 (The Pile)

Max Activating Token Index: 741

Text #9

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1964. Min Act: -0.0000

Data Index: 1366282 (The Pile)

Max Activating Token Index: 853

Text #10

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1790. Min Act: -0.0000

Data Index: 206822 (The Pile)

Max Activating Token Index: 751

Text #11

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1764. Min Act: -0.0000

Data Index: 751181 (The Pile)

Max Activating Token Index: 903

Text #12

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1749. Min Act: -0.0000

Data Index: 1434637 (The Pile)

Max Activating Token Index: 924

Text #13

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1690. Min Act: -0.0000

Data Index: 1455088 (The Pile)

Max Activating Token Index: 903

Text #14

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1740. Min Act: -0.0000

Data Index: 498680 (The Pile)

Max Activating Token Index: 128

Text #15

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1823. Min Act: -0.0000

Data Index: 79587 (The Pile)

Max Activating Token Index: 862

Text #16

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1859. Min Act: -0.0000

Data Index: 1546866 (The Pile)

Max Activating Token Index: 987

Text #17

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1684. Min Act: -0.0000

Data Index: 61795 (The Pile)

Max Activating Token Index: 593

Text #18

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1741. Min Act: -0.0000

Data Index: 1534419 (The Pile)

Max Activating Token Index: 266

Text #19

Max Range: 0.2276. Min Range: -0.2276

Max Act: 0.1751. Min Act: 0.0000

Data Index: 228957 (The Pile)

Max Activating Token Index: 228