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

Dataset: The Pile

Neuron 1861 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.1143. Min Act: -0.0000

Data Index: 810133 (The Pile)

Max Activating Token Index: 100

Text #1

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0906. Min Act: -0.0000

Data Index: 325640 (The Pile)

Max Activating Token Index: 422

Text #2

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0924. Min Act: -0.0000

Data Index: 685236 (The Pile)

Max Activating Token Index: 49

Text #3

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0850. Min Act: -0.0000

Data Index: 327885 (The Pile)

Max Activating Token Index: 907

Text #4

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0773. Min Act: -0.0000

Data Index: 1604079 (The Pile)

Max Activating Token Index: 465

Text #5

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0748. Min Act: -0.0000

Data Index: 455442 (The Pile)

Max Activating Token Index: 549

Text #6

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0709. Min Act: -0.0000

Data Index: 265789 (The Pile)

Max Activating Token Index: 718

Text #7

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0712. Min Act: -0.0000

Data Index: 910450 (The Pile)

Max Activating Token Index: 182

Text #8

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0734. Min Act: -0.0000

Data Index: 738959 (The Pile)

Max Activating Token Index: 556

Text #9

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0732. Min Act: -0.0000

Data Index: 362475 (The Pile)

Max Activating Token Index: 924

Text #10

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0656. Min Act: -0.0000

Data Index: 683326 (The Pile)

Max Activating Token Index: 102

Text #11

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0602. Min Act: -0.0000

Data Index: 502931 (The Pile)

Max Activating Token Index: 610

Text #12

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0662. Min Act: -0.0000

Data Index: 1006095 (The Pile)

Max Activating Token Index: 625

Text #13

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0611. Min Act: -0.0000

Data Index: 1130240 (The Pile)

Max Activating Token Index: 309

Text #14

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0581. Min Act: -0.0000

Data Index: 1229022 (The Pile)

Max Activating Token Index: 661

Text #15

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0624. Min Act: -0.0000

Data Index: 1801047 (The Pile)

Max Activating Token Index: 709

Text #16

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0529. Min Act: -0.0000

Data Index: 1751664 (The Pile)

Max Activating Token Index: 848

Text #17

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0624. Min Act: -0.0000

Data Index: 1975864 (The Pile)

Max Activating Token Index: 298

Text #18

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0563. Min Act: -0.0000

Data Index: 644771 (The Pile)

Max Activating Token Index: 907

Text #19

Max Range: 0.1143. Min Range: -0.1143

Max Act: 0.0559. Min Act: -0.0000

Data Index: 1827071 (The Pile)

Max Activating Token Index: 995