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

Dataset: The Pile

Neuron 4010 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6428. Min Range: -1.6428

Max Act: 1.5259. Min Act: -0.0000

Data Index: 35924 (The Pile)

Max Activating Token Index: 900

Text #1

Max Range: 1.6428. Min Range: -1.6428

Max Act: 1.6428. Min Act: -0.0000

Data Index: 1420968 (The Pile)

Max Activating Token Index: 747

Text #2

Max Range: 1.6428. Min Range: -1.6428

Max Act: 1.6224. Min Act: -0.0000

Data Index: 779598 (The Pile)

Max Activating Token Index: 615

Text #3

Max Range: 1.6428. Min Range: -1.6428

Max Act: 1.3853. Min Act: -0.0000

Data Index: 1203068 (The Pile)

Max Activating Token Index: 928

Text #4

Max Range: 1.6428. Min Range: -1.6428

Max Act: 1.5427. Min Act: -0.0000

Data Index: 143064 (The Pile)

Max Activating Token Index: 696

Text #5

Max Range: 1.6428. Min Range: -1.6428

Max Act: 1.3367. Min Act: -0.0000

Data Index: 61606 (The Pile)

Max Activating Token Index: 391

Text #6

Max Range: 1.6428. Min Range: -1.6428

Max Act: 1.3782. Min Act: -0.0000

Data Index: 1621187 (The Pile)

Max Activating Token Index: 736

Text #7

Max Range: 1.6428. Min Range: -1.6428

Max Act: 1.1151. Min Act: -0.0000

Data Index: 74401 (The Pile)

Max Activating Token Index: 595

Text #8

Max Range: 1.6428. Min Range: -1.6428

Max Act: 1.5455. Min Act: -0.0000

Data Index: 1183586 (The Pile)

Max Activating Token Index: 1004

Text #9

Max Range: 1.6428. Min Range: -1.6428

Max Act: 1.3030. Min Act: -0.0000

Data Index: 814259 (The Pile)

Max Activating Token Index: 937

Text #10

Max Range: 1.6428. Min Range: -1.6428

Max Act: 1.1958. Min Act: -0.0000

Data Index: 1795285 (The Pile)

Max Activating Token Index: 296

Text #11

Max Range: 1.6428. Min Range: -1.6428

Max Act: 1.3888. Min Act: -0.0000

Data Index: 149999 (The Pile)

Max Activating Token Index: 869

Text #12

Max Range: 1.6428. Min Range: -1.6428

Max Act: 1.3736. Min Act: -0.0000

Data Index: 398830 (The Pile)

Max Activating Token Index: 396

Text #13

Max Range: 1.6428. Min Range: -1.6428

Max Act: 1.3575. Min Act: -0.0000

Data Index: 67102 (The Pile)

Max Activating Token Index: 462

Text #14

Max Range: 1.6428. Min Range: -1.6428

Max Act: 1.1457. Min Act: -0.0000

Data Index: 421160 (The Pile)

Max Activating Token Index: 685

Text #15

Max Range: 1.6428. Min Range: -1.6428

Max Act: 1.2926. Min Act: -0.0000

Data Index: 942250 (The Pile)

Max Activating Token Index: 854

Text #16

Max Range: 1.6428. Min Range: -1.6428

Max Act: 1.2260. Min Act: -0.0000

Data Index: 1478686 (The Pile)

Max Activating Token Index: 439

Text #17

Max Range: 1.6428. Min Range: -1.6428

Max Act: 1.1649. Min Act: -0.0000

Data Index: 804936 (The Pile)

Max Activating Token Index: 180

Text #18

Max Range: 1.6428. Min Range: -1.6428

Max Act: 1.2953. Min Act: -0.0000

Data Index: 884521 (The Pile)

Max Activating Token Index: 1010

Text #19

Max Range: 1.6428. Min Range: -1.6428

Max Act: 1.3153. Min Act: -0.0000

Data Index: 1828259 (The Pile)

Max Activating Token Index: 505