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

Dataset: The Pile

Neuron 2070 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: 0.8056. Min Range: -0.8056

Max Act: 0.7594. Min Act: -0.0000

Data Index: 756863 (The Pile)

Max Activating Token Index: 531

Text #1

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.8056. Min Act: -0.0000

Data Index: 1013164 (The Pile)

Max Activating Token Index: 547

Text #2

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7329. Min Act: -0.0000

Data Index: 1081152 (The Pile)

Max Activating Token Index: 769

Text #3

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7663. Min Act: -0.0000

Data Index: 446652 (The Pile)

Max Activating Token Index: 538

Text #4

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.6734. Min Act: -0.0000

Data Index: 224457 (The Pile)

Max Activating Token Index: 534

Text #5

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.6756. Min Act: -0.0000

Data Index: 527237 (The Pile)

Max Activating Token Index: 637

Text #6

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7707. Min Act: -0.0000

Data Index: 1716906 (The Pile)

Max Activating Token Index: 612

Text #7

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1760712 (The Pile)

Max Activating Token Index: 479

Text #8

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7195. Min Act: -0.0000

Data Index: 1966867 (The Pile)

Max Activating Token Index: 479

Text #9

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1746195 (The Pile)

Max Activating Token Index: 803

Text #10

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7769. Min Act: -0.0000

Data Index: 1503316 (The Pile)

Max Activating Token Index: 656

Text #11

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.6766. Min Act: -0.0000

Data Index: 515062 (The Pile)

Max Activating Token Index: 590

Text #12

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7163. Min Act: -0.0000

Data Index: 318480 (The Pile)

Max Activating Token Index: 842

Text #13

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7144. Min Act: -0.0000

Data Index: 1903041 (The Pile)

Max Activating Token Index: 851

Text #14

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7059. Min Act: -0.0000

Data Index: 216473 (The Pile)

Max Activating Token Index: 953

Text #15

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.6991. Min Act: -0.0000

Data Index: 798381 (The Pile)

Max Activating Token Index: 555

Text #16

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.7266. Min Act: -0.0000

Data Index: 1418867 (The Pile)

Max Activating Token Index: 611

Text #17

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.6992. Min Act: -0.0000

Data Index: 349803 (The Pile)

Max Activating Token Index: 73

Text #18

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.6877. Min Act: -0.0000

Data Index: 949627 (The Pile)

Max Activating Token Index: 255

Text #19

Max Range: 0.8056. Min Range: -0.8056

Max Act: 0.6605. Min Act: -0.0000

Data Index: 650159 (The Pile)

Max Activating Token Index: 529