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

Dataset: The Pile

Neuron 213 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.5514. Min Act: -0.0000

Data Index: 772819 (The Pile)

Max Activating Token Index: 978

Text #1

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.2875. Min Act: 0.0000

Data Index: 272430 (The Pile)

Max Activating Token Index: 715

Text #2

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.3630. Min Act: -0.0000

Data Index: 723665 (The Pile)

Max Activating Token Index: 323

Text #3

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.3508. Min Act: -0.0000

Data Index: 1235830 (The Pile)

Max Activating Token Index: 608

Text #4

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.3909. Min Act: 0.0000

Data Index: 867345 (The Pile)

Max Activating Token Index: 518

Text #5

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.2392. Min Act: -0.0000

Data Index: 573765 (The Pile)

Max Activating Token Index: 155

Text #6

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.3593. Min Act: -0.0000

Data Index: 874950 (The Pile)

Max Activating Token Index: 456

Text #7

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.2556. Min Act: -0.0000

Data Index: 1512615 (The Pile)

Max Activating Token Index: 993

Text #8

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.1842. Min Act: -0.0000

Data Index: 541660 (The Pile)

Max Activating Token Index: 157

Text #9

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.2375. Min Act: -0.0000

Data Index: 1669365 (The Pile)

Max Activating Token Index: 326

Text #10

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.3015. Min Act: -0.0000

Data Index: 157195 (The Pile)

Max Activating Token Index: 153

Text #11

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.2228. Min Act: -0.0000

Data Index: 657135 (The Pile)

Max Activating Token Index: 94

Text #12

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.2056. Min Act: -0.0000

Data Index: 121089 (The Pile)

Max Activating Token Index: 798

Text #13

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.1983. Min Act: -0.0000

Data Index: 446495 (The Pile)

Max Activating Token Index: 681

Text #14

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.1972. Min Act: -0.0000

Data Index: 547479 (The Pile)

Max Activating Token Index: 117

Text #15

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.1671. Min Act: -0.0000

Data Index: 962870 (The Pile)

Max Activating Token Index: 617

Text #16

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.1539. Min Act: -0.0000

Data Index: 1856968 (The Pile)

Max Activating Token Index: 840

Text #17

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.0910. Min Act: -0.0000

Data Index: 815173 (The Pile)

Max Activating Token Index: 425

Text #18

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.1309. Min Act: -0.0000

Data Index: 1534742 (The Pile)

Max Activating Token Index: 665

Text #19

Max Range: 1.5514. Min Range: -1.5514

Max Act: 1.0775. Min Act: -0.0000

Data Index: 1918414 (The Pile)

Max Activating Token Index: 352