Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 419 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.4791. Min Act: -0.0000

Data Index: 734799 (The Pile)

Max Activating Token Index: 208

Text #1

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.1942. Min Act: -0.0000

Data Index: 1550787 (The Pile)

Max Activating Token Index: 734

Text #2

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.1953. Min Act: -0.0000

Data Index: 1177250 (The Pile)

Max Activating Token Index: 472

Text #3

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.1965. Min Act: -0.0000

Data Index: 1732192 (The Pile)

Max Activating Token Index: 674

Text #4

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.1922. Min Act: -0.0000

Data Index: 969094 (The Pile)

Max Activating Token Index: 762

Text #5

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.2117. Min Act: -0.0000

Data Index: 805317 (The Pile)

Max Activating Token Index: 133

Text #6

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.1854. Min Act: -0.0000

Data Index: 928175 (The Pile)

Max Activating Token Index: 300

Text #7

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.2049. Min Act: -0.0000

Data Index: 761982 (The Pile)

Max Activating Token Index: 634

Text #8

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.1826. Min Act: -0.0000

Data Index: 850047 (The Pile)

Max Activating Token Index: 218

Text #9

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.1594. Min Act: -0.0000

Data Index: 40272 (The Pile)

Max Activating Token Index: 380

Text #10

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.1725. Min Act: -0.0000

Data Index: 388703 (The Pile)

Max Activating Token Index: 713

Text #11

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.1949. Min Act: -0.0000

Data Index: 206894 (The Pile)

Max Activating Token Index: 692

Text #12

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.1694. Min Act: -0.0000

Data Index: 323146 (The Pile)

Max Activating Token Index: 266

Text #13

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.1722. Min Act: -0.0000

Data Index: 529670 (The Pile)

Max Activating Token Index: 757

Text #14

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.1730. Min Act: -0.0000

Data Index: 158363 (The Pile)

Max Activating Token Index: 716

Text #15

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.1753. Min Act: -0.0000

Data Index: 630872 (The Pile)

Max Activating Token Index: 1002

Text #16

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.1785. Min Act: -0.0000

Data Index: 1113647 (The Pile)

Max Activating Token Index: 537

Text #17

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.1647. Min Act: -0.0000

Data Index: 1702918 (The Pile)

Max Activating Token Index: 971

Text #18

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.1622. Min Act: -0.0000

Data Index: 989060 (The Pile)

Max Activating Token Index: 379

Text #19

Max Range: 0.4791. Min Range: -0.4791

Max Act: 0.1755. Min Act: -0.0000

Data Index: 1920047 (The Pile)

Max Activating Token Index: 602