Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2498 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1096. Min Act: -0.0000

Data Index: 1969670 (The Pile)

Max Activating Token Index: 865

Text #1

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1068. Min Act: -0.0000

Data Index: 1142159 (The Pile)

Max Activating Token Index: 623

Text #2

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0945. Min Act: -0.0000

Data Index: 1446271 (The Pile)

Max Activating Token Index: 510

Text #3

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0916. Min Act: -0.0000

Data Index: 961027 (The Pile)

Max Activating Token Index: 971

Text #4

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0886. Min Act: -0.0000

Data Index: 324776 (The Pile)

Max Activating Token Index: 618

Text #5

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0839. Min Act: -0.0000

Data Index: 250645 (The Pile)

Max Activating Token Index: 90

Text #6

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0886. Min Act: -0.0000

Data Index: 338648 (The Pile)

Max Activating Token Index: 858

Text #7

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0780. Min Act: -0.0000

Data Index: 1990841 (The Pile)

Max Activating Token Index: 680

Text #8

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0751. Min Act: -0.0000

Data Index: 695902 (The Pile)

Max Activating Token Index: 646

Text #9

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0771. Min Act: -0.0000

Data Index: 67549 (The Pile)

Max Activating Token Index: 51

Text #10

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0796. Min Act: -0.0000

Data Index: 1557872 (The Pile)

Max Activating Token Index: 609

Text #11

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0785. Min Act: -0.0000

Data Index: 87630 (The Pile)

Max Activating Token Index: 225

Text #12

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0783. Min Act: -0.0000

Data Index: 1237299 (The Pile)

Max Activating Token Index: 628

Text #13

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0769. Min Act: -0.0000

Data Index: 1953481 (The Pile)

Max Activating Token Index: 857

Text #14

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0789. Min Act: -0.0000

Data Index: 1750242 (The Pile)

Max Activating Token Index: 309

Text #15

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0793. Min Act: -0.0000

Data Index: 263550 (The Pile)

Max Activating Token Index: 756

Text #16

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0733. Min Act: -0.0000

Data Index: 1648872 (The Pile)

Max Activating Token Index: 443

Text #17

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0751. Min Act: -0.0000

Data Index: 1869781 (The Pile)

Max Activating Token Index: 773

Text #18

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0721. Min Act: -0.0000

Data Index: 210348 (The Pile)

Max Activating Token Index: 489

Text #19

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0741. Min Act: -0.0000

Data Index: 626893 (The Pile)

Max Activating Token Index: 197