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

Dataset: The Pile

Neuron 1444 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: 1.1753. Min Range: -1.1753

Max Act: 1.1753. Min Act: -0.0000

Data Index: 1392222 (The Pile)

Max Activating Token Index: 342

Text #1

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9914. Min Act: -0.0000

Data Index: 191116 (The Pile)

Max Activating Token Index: 574

Text #2

Max Range: 1.1753. Min Range: -1.1753

Max Act: 1.0808. Min Act: -0.0000

Data Index: 301076 (The Pile)

Max Activating Token Index: 87

Text #3

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9949. Min Act: -0.0000

Data Index: 747065 (The Pile)

Max Activating Token Index: 163

Text #4

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9914. Min Act: -0.0000

Data Index: 695859 (The Pile)

Max Activating Token Index: 633

Text #5

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9228. Min Act: -0.0000

Data Index: 666173 (The Pile)

Max Activating Token Index: 370

Text #6

Max Range: 1.1753. Min Range: -1.1753

Max Act: 1.0151. Min Act: -0.0000

Data Index: 64415 (The Pile)

Max Activating Token Index: 1000

Text #7

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9653. Min Act: -0.0000

Data Index: 733498 (The Pile)

Max Activating Token Index: 613

Text #8

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9598. Min Act: -0.0000

Data Index: 1416783 (The Pile)

Max Activating Token Index: 531

Text #9

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.8393. Min Act: -0.0000

Data Index: 429752 (The Pile)

Max Activating Token Index: 553

Text #10

Max Range: 1.1753. Min Range: -1.1753

Max Act: 1.0487. Min Act: -0.0000

Data Index: 1600509 (The Pile)

Max Activating Token Index: 326

Text #11

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9407. Min Act: -0.0000

Data Index: 1120418 (The Pile)

Max Activating Token Index: 859

Text #12

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.8840. Min Act: -0.0000

Data Index: 393223 (The Pile)

Max Activating Token Index: 309

Text #13

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.8952. Min Act: -0.0000

Data Index: 10967 (The Pile)

Max Activating Token Index: 670

Text #14

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9351. Min Act: -0.0000

Data Index: 893059 (The Pile)

Max Activating Token Index: 737

Text #15

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.8556. Min Act: -0.0000

Data Index: 1851681 (The Pile)

Max Activating Token Index: 660

Text #16

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.8557. Min Act: -0.0000

Data Index: 1500873 (The Pile)

Max Activating Token Index: 618

Text #17

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.8525. Min Act: -0.0000

Data Index: 1411877 (The Pile)

Max Activating Token Index: 575

Text #18

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.9827. Min Act: -0.0000

Data Index: 647049 (The Pile)

Max Activating Token Index: 930

Text #19

Max Range: 1.1753. Min Range: -1.1753

Max Act: 0.8833. Min Act: -0.0000

Data Index: 1020473 (The Pile)

Max Activating Token Index: 181