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

Dataset: The Pile

Neuron 2561 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: 0.9950. Min Range: -0.9950

Max Act: 0.9950. Min Act: -0.0000

Data Index: 1113647 (The Pile)

Max Activating Token Index: 946

Text #1

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7652. Min Act: -0.0000

Data Index: 710838 (The Pile)

Max Activating Token Index: 743

Text #2

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7335. Min Act: -0.0000

Data Index: 1825365 (The Pile)

Max Activating Token Index: 780

Text #3

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7531. Min Act: -0.0000

Data Index: 1728772 (The Pile)

Max Activating Token Index: 405

Text #4

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7758. Min Act: -0.0000

Data Index: 748314 (The Pile)

Max Activating Token Index: 514

Text #5

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7119. Min Act: -0.0000

Data Index: 158363 (The Pile)

Max Activating Token Index: 793

Text #6

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7692. Min Act: -0.0000

Data Index: 1558486 (The Pile)

Max Activating Token Index: 76

Text #7

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.6819. Min Act: -0.0000

Data Index: 666110 (The Pile)

Max Activating Token Index: 955

Text #8

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7243. Min Act: -0.0000

Data Index: 311832 (The Pile)

Max Activating Token Index: 534

Text #9

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.6792. Min Act: -0.0000

Data Index: 317161 (The Pile)

Max Activating Token Index: 633

Text #10

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.6707. Min Act: -0.0000

Data Index: 1884991 (The Pile)

Max Activating Token Index: 596

Text #11

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1325521 (The Pile)

Max Activating Token Index: 913

Text #12

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7364. Min Act: -0.0000

Data Index: 212964 (The Pile)

Max Activating Token Index: 49

Text #13

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7282. Min Act: -0.0000

Data Index: 837015 (The Pile)

Max Activating Token Index: 26

Text #14

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.7724. Min Act: -0.0000

Data Index: 40272 (The Pile)

Max Activating Token Index: 679

Text #15

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.6460. Min Act: -0.0000

Data Index: 1220870 (The Pile)

Max Activating Token Index: 1000

Text #16

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.6873. Min Act: -0.0000

Data Index: 226650 (The Pile)

Max Activating Token Index: 780

Text #17

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.6845. Min Act: -0.0000

Data Index: 830202 (The Pile)

Max Activating Token Index: 1004

Text #18

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.6614. Min Act: -0.0000

Data Index: 1600216 (The Pile)

Max Activating Token Index: 532

Text #19

Max Range: 0.9950. Min Range: -0.9950

Max Act: 0.6811. Min Act: -0.0000

Data Index: 780615 (The Pile)

Max Activating Token Index: 248