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

Dataset: The Pile

Neuron 752 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: 0.1081. Min Range: -0.1081

Max Act: 0.1081. Min Act: -0.0000

Data Index: 1718777 (The Pile)

Max Activating Token Index: 76

Text #1

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.1027. Min Act: -0.0000

Data Index: 28766 (The Pile)

Max Activating Token Index: 180

Text #2

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0961. Min Act: -0.0000

Data Index: 1513248 (The Pile)

Max Activating Token Index: 150

Text #3

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0806. Min Act: -0.0000

Data Index: 1794937 (The Pile)

Max Activating Token Index: 23

Text #4

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1856016 (The Pile)

Max Activating Token Index: 311

Text #5

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0736. Min Act: -0.0000

Data Index: 1188325 (The Pile)

Max Activating Token Index: 958

Text #6

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0790. Min Act: -0.0000

Data Index: 1322074 (The Pile)

Max Activating Token Index: 88

Text #7

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0694. Min Act: -0.0000

Data Index: 1563777 (The Pile)

Max Activating Token Index: 830

Text #8

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0727. Min Act: -0.0000

Data Index: 590829 (The Pile)

Max Activating Token Index: 869

Text #9

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0773. Min Act: -0.0000

Data Index: 812297 (The Pile)

Max Activating Token Index: 978

Text #10

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0763. Min Act: -0.0000

Data Index: 260958 (The Pile)

Max Activating Token Index: 341

Text #11

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0843. Min Act: -0.0000

Data Index: 807285 (The Pile)

Max Activating Token Index: 476

Text #12

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0771. Min Act: -0.0000

Data Index: 1533635 (The Pile)

Max Activating Token Index: 40

Text #13

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0763. Min Act: -0.0000

Data Index: 1791534 (The Pile)

Max Activating Token Index: 918

Text #14

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0808. Min Act: -0.0000

Data Index: 25639 (The Pile)

Max Activating Token Index: 194

Text #15

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0681. Min Act: -0.0000

Data Index: 1360345 (The Pile)

Max Activating Token Index: 398

Text #16

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0715. Min Act: -0.0000

Data Index: 1387244 (The Pile)

Max Activating Token Index: 743

Text #17

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0659. Min Act: -0.0000

Data Index: 1538757 (The Pile)

Max Activating Token Index: 912

Text #18

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0732. Min Act: -0.0000

Data Index: 1821706 (The Pile)

Max Activating Token Index: 388

Text #19

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0678. Min Act: -0.0000

Data Index: 381583 (The Pile)

Max Activating Token Index: 384