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

Dataset: The Pile

Neuron 1908 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: 0.5224. Min Range: -0.5224

Max Act: 0.5224. Min Act: -0.0000

Data Index: 809721 (The Pile)

Max Activating Token Index: 934

Text #1

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3389. Min Act: -0.0000

Data Index: 1822097 (The Pile)

Max Activating Token Index: 313

Text #2

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3212. Min Act: -0.0000

Data Index: 1964974 (The Pile)

Max Activating Token Index: 717

Text #3

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3167. Min Act: -0.0000

Data Index: 783392 (The Pile)

Max Activating Token Index: 598

Text #4

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.2737. Min Act: -0.0000

Data Index: 1483565 (The Pile)

Max Activating Token Index: 808

Text #5

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3215. Min Act: -0.0000

Data Index: 653405 (The Pile)

Max Activating Token Index: 538

Text #6

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3052. Min Act: -0.0000

Data Index: 408315 (The Pile)

Max Activating Token Index: 816

Text #7

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.2965. Min Act: -0.0000

Data Index: 415385 (The Pile)

Max Activating Token Index: 802

Text #8

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.2676. Min Act: -0.0000

Data Index: 1923802 (The Pile)

Max Activating Token Index: 444

Text #9

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.2526. Min Act: -0.0000

Data Index: 869870 (The Pile)

Max Activating Token Index: 275

Text #10

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.2537. Min Act: -0.0000

Data Index: 673455 (The Pile)

Max Activating Token Index: 568

Text #11

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.2554. Min Act: -0.0000

Data Index: 1239733 (The Pile)

Max Activating Token Index: 750

Text #12

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.2811. Min Act: -0.0000

Data Index: 334964 (The Pile)

Max Activating Token Index: 436

Text #13

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.2784. Min Act: -0.0000

Data Index: 1391784 (The Pile)

Max Activating Token Index: 817

Text #14

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.2908. Min Act: -0.0000

Data Index: 639806 (The Pile)

Max Activating Token Index: 679

Text #15

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.2674. Min Act: -0.0000

Data Index: 275034 (The Pile)

Max Activating Token Index: 845

Text #16

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.2819. Min Act: -0.0000

Data Index: 599125 (The Pile)

Max Activating Token Index: 563

Text #17

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1042731 (The Pile)

Max Activating Token Index: 961

Text #18

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.2559. Min Act: -0.0000

Data Index: 980882 (The Pile)

Max Activating Token Index: 272

Text #19

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.2348. Min Act: -0.0000

Data Index: 877208 (The Pile)

Max Activating Token Index: 547