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

Dataset: The Pile

Neuron 2759 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3703. Min Range: -1.3703

Max Act: 1.3703. Min Act: -0.0000

Data Index: 1199652 (The Pile)

Max Activating Token Index: 530

Text #1

Max Range: 1.3703. Min Range: -1.3703

Max Act: 1.1244. Min Act: -0.0000

Data Index: 1335921 (The Pile)

Max Activating Token Index: 674

Text #2

Max Range: 1.3703. Min Range: -1.3703

Max Act: 1.1166. Min Act: -0.0000

Data Index: 1918833 (The Pile)

Max Activating Token Index: 249

Text #3

Max Range: 1.3703. Min Range: -1.3703

Max Act: 1.1897. Min Act: -0.0000

Data Index: 1785234 (The Pile)

Max Activating Token Index: 190

Text #4

Max Range: 1.3703. Min Range: -1.3703

Max Act: 1.0550. Min Act: -0.0000

Data Index: 1889462 (The Pile)

Max Activating Token Index: 130

Text #5

Max Range: 1.3703. Min Range: -1.3703

Max Act: 1.0475. Min Act: -0.0000

Data Index: 808509 (The Pile)

Max Activating Token Index: 479

Text #6

Max Range: 1.3703. Min Range: -1.3703

Max Act: 0.9920. Min Act: -0.0000

Data Index: 785922 (The Pile)

Max Activating Token Index: 70

Text #7

Max Range: 1.3703. Min Range: -1.3703

Max Act: 1.0069. Min Act: -0.0000

Data Index: 1166746 (The Pile)

Max Activating Token Index: 114

Text #8

Max Range: 1.3703. Min Range: -1.3703

Max Act: 0.9346. Min Act: -0.0000

Data Index: 820896 (The Pile)

Max Activating Token Index: 783

Text #9

Max Range: 1.3703. Min Range: -1.3703

Max Act: 0.8928. Min Act: -0.0000

Data Index: 1931500 (The Pile)

Max Activating Token Index: 879

Text #10

Max Range: 1.3703. Min Range: -1.3703

Max Act: 0.9956. Min Act: -0.0000

Data Index: 1131002 (The Pile)

Max Activating Token Index: 378

Text #11

Max Range: 1.3703. Min Range: -1.3703

Max Act: 0.9496. Min Act: -0.0000

Data Index: 709801 (The Pile)

Max Activating Token Index: 148

Text #12

Max Range: 1.3703. Min Range: -1.3703

Max Act: 0.9796. Min Act: -0.0000

Data Index: 1950526 (The Pile)

Max Activating Token Index: 788

Text #13

Max Range: 1.3703. Min Range: -1.3703

Max Act: 0.8842. Min Act: -0.0000

Data Index: 1001974 (The Pile)

Max Activating Token Index: 897

Text #14

Max Range: 1.3703. Min Range: -1.3703

Max Act: 0.8843. Min Act: -0.0000

Data Index: 907955 (The Pile)

Max Activating Token Index: 328

Text #15

Max Range: 1.3703. Min Range: -1.3703

Max Act: 0.8553. Min Act: -0.0000

Data Index: 480297 (The Pile)

Max Activating Token Index: 932

Text #16

Max Range: 1.3703. Min Range: -1.3703

Max Act: 0.8289. Min Act: -0.0000

Data Index: 160150 (The Pile)

Max Activating Token Index: 744

Text #17

Max Range: 1.3703. Min Range: -1.3703

Max Act: 0.9112. Min Act: -0.0000

Data Index: 523143 (The Pile)

Max Activating Token Index: 848

Text #18

Max Range: 1.3703. Min Range: -1.3703

Max Act: 0.7775. Min Act: -0.0000

Data Index: 1248034 (The Pile)

Max Activating Token Index: 126

Text #19

Max Range: 1.3703. Min Range: -1.3703

Max Act: 0.8497. Min Act: -0.0000

Data Index: 423704 (The Pile)

Max Activating Token Index: 611