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

Dataset: The Pile

Neuron 3136 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: 0.5228. Min Range: -0.5228

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1675977 (The Pile)

Max Activating Token Index: 704

Text #1

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.5026. Min Act: -0.0000

Data Index: 1335171 (The Pile)

Max Activating Token Index: 899

Text #2

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.5058. Min Act: -0.0000

Data Index: 57396 (The Pile)

Max Activating Token Index: 706

Text #3

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.5111. Min Act: -0.0000

Data Index: 1198549 (The Pile)

Max Activating Token Index: 912

Text #4

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4651. Min Act: -0.0000

Data Index: 600510 (The Pile)

Max Activating Token Index: 68

Text #5

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4347. Min Act: -0.0000

Data Index: 553855 (The Pile)

Max Activating Token Index: 412

Text #6

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4923. Min Act: -0.0000

Data Index: 567676 (The Pile)

Max Activating Token Index: 757

Text #7

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4491. Min Act: -0.0000

Data Index: 1451854 (The Pile)

Max Activating Token Index: 154

Text #8

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4370. Min Act: -0.0000

Data Index: 686273 (The Pile)

Max Activating Token Index: 647

Text #9

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4209. Min Act: -0.0000

Data Index: 166814 (The Pile)

Max Activating Token Index: 258

Text #10

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4434. Min Act: -0.0000

Data Index: 1625682 (The Pile)

Max Activating Token Index: 247

Text #11

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4599. Min Act: -0.0000

Data Index: 726556 (The Pile)

Max Activating Token Index: 644

Text #12

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4128. Min Act: -0.0000

Data Index: 587846 (The Pile)

Max Activating Token Index: 196

Text #13

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4116. Min Act: -0.0000

Data Index: 102044 (The Pile)

Max Activating Token Index: 461

Text #14

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4155. Min Act: -0.0000

Data Index: 996692 (The Pile)

Max Activating Token Index: 74

Text #15

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4346. Min Act: -0.0000

Data Index: 1342687 (The Pile)

Max Activating Token Index: 656

Text #16

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1500966 (The Pile)

Max Activating Token Index: 904

Text #17

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1036025 (The Pile)

Max Activating Token Index: 270

Text #18

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4704. Min Act: -0.0000

Data Index: 895088 (The Pile)

Max Activating Token Index: 607

Text #19

Max Range: 0.5228. Min Range: -0.5228

Max Act: 0.4409. Min Act: -0.0000

Data Index: 1279909 (The Pile)

Max Activating Token Index: 318