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

Dataset: The Pile

Neuron 1807 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: 0.3688. Min Range: -0.3688

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1160495 (The Pile)

Max Activating Token Index: 181

Text #1

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3688. Min Act: -0.0000

Data Index: 1653688 (The Pile)

Max Activating Token Index: 673

Text #2

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2671. Min Act: -0.0000

Data Index: 931561 (The Pile)

Max Activating Token Index: 617

Text #3

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2514. Min Act: -0.0000

Data Index: 850291 (The Pile)

Max Activating Token Index: 224

Text #4

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2438. Min Act: -0.0000

Data Index: 1263560 (The Pile)

Max Activating Token Index: 118

Text #5

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2465. Min Act: -0.0000

Data Index: 297478 (The Pile)

Max Activating Token Index: 823

Text #6

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2426. Min Act: -0.0000

Data Index: 199215 (The Pile)

Max Activating Token Index: 141

Text #7

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2359. Min Act: -0.0000

Data Index: 786595 (The Pile)

Max Activating Token Index: 286

Text #8

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2397. Min Act: -0.0000

Data Index: 1964577 (The Pile)

Max Activating Token Index: 832

Text #9

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2201. Min Act: -0.0000

Data Index: 1903709 (The Pile)

Max Activating Token Index: 746

Text #10

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.1991. Min Act: -0.0000

Data Index: 807296 (The Pile)

Max Activating Token Index: 925

Text #11

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2181. Min Act: -0.0000

Data Index: 1257581 (The Pile)

Max Activating Token Index: 524

Text #12

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2265. Min Act: -0.0000

Data Index: 967923 (The Pile)

Max Activating Token Index: 695

Text #13

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.1988. Min Act: -0.0000

Data Index: 348776 (The Pile)

Max Activating Token Index: 573

Text #14

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2011. Min Act: -0.0000

Data Index: 1217329 (The Pile)

Max Activating Token Index: 113

Text #15

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1327746 (The Pile)

Max Activating Token Index: 710

Text #16

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2100. Min Act: -0.0000

Data Index: 377995 (The Pile)

Max Activating Token Index: 20

Text #17

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.1948. Min Act: -0.0000

Data Index: 891640 (The Pile)

Max Activating Token Index: 101

Text #18

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.1840. Min Act: -0.0000

Data Index: 1541074 (The Pile)

Max Activating Token Index: 623

Text #19

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.2051. Min Act: -0.0000

Data Index: 1120606 (The Pile)

Max Activating Token Index: 985