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

Dataset: The Pile

Neuron 70 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.0574. Min Range: -1.0574

Max Act: 1.0574. Min Act: -0.0000

Data Index: 318752 (The Pile)

Max Activating Token Index: 373

Text #1

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.9808. Min Act: -0.0000

Data Index: 1937844 (The Pile)

Max Activating Token Index: 342

Text #2

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8449. Min Act: -0.0000

Data Index: 1198197 (The Pile)

Max Activating Token Index: 785

Text #3

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.9594. Min Act: -0.0000

Data Index: 674159 (The Pile)

Max Activating Token Index: 335

Text #4

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8707. Min Act: -0.0000

Data Index: 1447876 (The Pile)

Max Activating Token Index: 238

Text #5

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.9051. Min Act: -0.0000

Data Index: 1302150 (The Pile)

Max Activating Token Index: 777

Text #6

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8361. Min Act: -0.0000

Data Index: 256166 (The Pile)

Max Activating Token Index: 943

Text #7

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8725. Min Act: -0.0000

Data Index: 1950573 (The Pile)

Max Activating Token Index: 946

Text #8

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1644484 (The Pile)

Max Activating Token Index: 474

Text #9

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.9053. Min Act: -0.0000

Data Index: 728671 (The Pile)

Max Activating Token Index: 447

Text #10

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8813. Min Act: -0.0000

Data Index: 1879019 (The Pile)

Max Activating Token Index: 403

Text #11

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.9194. Min Act: -0.0000

Data Index: 502527 (The Pile)

Max Activating Token Index: 452

Text #12

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8782. Min Act: -0.0000

Data Index: 878418 (The Pile)

Max Activating Token Index: 511

Text #13

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.9044. Min Act: -0.0000

Data Index: 738848 (The Pile)

Max Activating Token Index: 832

Text #14

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8694. Min Act: -0.0000

Data Index: 514774 (The Pile)

Max Activating Token Index: 413

Text #15

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8351. Min Act: -0.0000

Data Index: 977022 (The Pile)

Max Activating Token Index: 273

Text #16

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.7856. Min Act: -0.0000

Data Index: 1592287 (The Pile)

Max Activating Token Index: 76

Text #17

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.8992. Min Act: -0.0000

Data Index: 1353352 (The Pile)

Max Activating Token Index: 721

Text #18

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.7981. Min Act: -0.0000

Data Index: 612162 (The Pile)

Max Activating Token Index: 424

Text #19

Max Range: 1.0574. Min Range: -1.0574

Max Act: 0.7991. Min Act: -0.0000

Data Index: 1865853 (The Pile)

Max Activating Token Index: 415