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

Dataset: The Pile

Neuron 2986 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: 0.6704. Min Range: -0.6704

Max Act: 0.6704. Min Act: -0.0000

Data Index: 1934886 (The Pile)

Max Activating Token Index: 437

Text #1

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.6068. Min Act: -0.0000

Data Index: 612922 (The Pile)

Max Activating Token Index: 678

Text #2

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1248450 (The Pile)

Max Activating Token Index: 726

Text #3

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.5951. Min Act: -0.0000

Data Index: 511434 (The Pile)

Max Activating Token Index: 242

Text #4

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1372396 (The Pile)

Max Activating Token Index: 432

Text #5

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.5651. Min Act: -0.0000

Data Index: 1143675 (The Pile)

Max Activating Token Index: 131

Text #6

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.5703. Min Act: -0.0000

Data Index: 357619 (The Pile)

Max Activating Token Index: 816

Text #7

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.5278. Min Act: -0.0000

Data Index: 758910 (The Pile)

Max Activating Token Index: 221

Text #8

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.5899. Min Act: -0.0000

Data Index: 540432 (The Pile)

Max Activating Token Index: 98

Text #9

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1977407 (The Pile)

Max Activating Token Index: 774

Text #10

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1647970 (The Pile)

Max Activating Token Index: 439

Text #11

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.5074. Min Act: -0.0000

Data Index: 1100515 (The Pile)

Max Activating Token Index: 252

Text #12

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.4952. Min Act: -0.0000

Data Index: 1062986 (The Pile)

Max Activating Token Index: 716

Text #13

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.4991. Min Act: -0.0000

Data Index: 1256524 (The Pile)

Max Activating Token Index: 311

Text #14

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.5181. Min Act: -0.0000

Data Index: 1102281 (The Pile)

Max Activating Token Index: 390

Text #15

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.4814. Min Act: -0.0000

Data Index: 1542386 (The Pile)

Max Activating Token Index: 739

Text #16

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.5237. Min Act: -0.0000

Data Index: 968308 (The Pile)

Max Activating Token Index: 652

Text #17

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.4427. Min Act: -0.0000

Data Index: 826923 (The Pile)

Max Activating Token Index: 546

Text #18

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.4562. Min Act: -0.0000

Data Index: 1992118 (The Pile)

Max Activating Token Index: 572

Text #19

Max Range: 0.6704. Min Range: -0.6704

Max Act: 0.4946. Min Act: -0.0000

Data Index: 1702021 (The Pile)

Max Activating Token Index: 698