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

Dataset: The Pile

Neuron 553 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: 4.1945. Min Range: -4.1945

Max Act: 4.1945. Min Act: -0.0000

Data Index: 101589 (The Pile)

Max Activating Token Index: 346

Text #1

Max Range: 4.1945. Min Range: -4.1945

Max Act: 4.0408. Min Act: -0.0000

Data Index: 1005648 (The Pile)

Max Activating Token Index: 927

Text #2

Max Range: 4.1945. Min Range: -4.1945

Max Act: 3.5178. Min Act: -0.0000

Data Index: 492521 (The Pile)

Max Activating Token Index: 896

Text #3

Max Range: 4.1945. Min Range: -4.1945

Max Act: 3.3725. Min Act: -0.0000

Data Index: 1834908 (The Pile)

Max Activating Token Index: 894

Text #4

Max Range: 4.1945. Min Range: -4.1945

Max Act: 3.6039. Min Act: -0.0000

Data Index: 1884729 (The Pile)

Max Activating Token Index: 662

Text #5

Max Range: 4.1945. Min Range: -4.1945

Max Act: 3.5217. Min Act: -0.0000

Data Index: 1711174 (The Pile)

Max Activating Token Index: 124

Text #6

Max Range: 4.1945. Min Range: -4.1945

Max Act: 3.2844. Min Act: -0.0000

Data Index: 1342287 (The Pile)

Max Activating Token Index: 454

Text #7

Max Range: 4.1945. Min Range: -4.1945

Max Act: 3.4169. Min Act: -0.0000

Data Index: 524779 (The Pile)

Max Activating Token Index: 976

Text #8

Max Range: 4.1945. Min Range: -4.1945

Max Act: 3.0393. Min Act: -0.0000

Data Index: 747638 (The Pile)

Max Activating Token Index: 924

Text #9

Max Range: 4.1945. Min Range: -4.1945

Max Act: 3.6639. Min Act: -0.0000

Data Index: 76763 (The Pile)

Max Activating Token Index: 52

Text #10

Max Range: 4.1945. Min Range: -4.1945

Max Act: 3.4501. Min Act: -0.0000

Data Index: 1375977 (The Pile)

Max Activating Token Index: 638

Text #11

Max Range: 4.1945. Min Range: -4.1945

Max Act: 3.1465. Min Act: -0.0000

Data Index: 1829227 (The Pile)

Max Activating Token Index: 750

Text #12

Max Range: 4.1945. Min Range: -4.1945

Max Act: 3.4235. Min Act: -0.0000

Data Index: 181215 (The Pile)

Max Activating Token Index: 462

Text #13

Max Range: 4.1945. Min Range: -4.1945

Max Act: 3.1301. Min Act: -0.0000

Data Index: 62729 (The Pile)

Max Activating Token Index: 653

Text #14

Max Range: 4.1945. Min Range: -4.1945

Max Act: 3.0434. Min Act: -0.0000

Data Index: 509186 (The Pile)

Max Activating Token Index: 346

Text #15

Max Range: 4.1945. Min Range: -4.1945

Max Act: 3.0566. Min Act: -0.0000

Data Index: 442076 (The Pile)

Max Activating Token Index: 710

Text #16

Max Range: 4.1945. Min Range: -4.1945

Max Act: 2.8796. Min Act: -0.0000

Data Index: 1899056 (The Pile)

Max Activating Token Index: 937

Text #17

Max Range: 4.1945. Min Range: -4.1945

Max Act: 2.8708. Min Act: -0.0000

Data Index: 1569476 (The Pile)

Max Activating Token Index: 913

Text #18

Max Range: 4.1945. Min Range: -4.1945

Max Act: 3.2195. Min Act: -0.0000

Data Index: 806956 (The Pile)

Max Activating Token Index: 722

Text #19

Max Range: 4.1945. Min Range: -4.1945

Max Act: 3.2340. Min Act: -0.0000

Data Index: 743047 (The Pile)

Max Activating Token Index: 123