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

Dataset: The Pile

Neuron 3937 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.5071. Min Act: -0.0000

Data Index: 589013 (The Pile)

Max Activating Token Index: 859

Text #1

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.4749. Min Act: -0.0000

Data Index: 1937382 (The Pile)

Max Activating Token Index: 918

Text #2

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.4459. Min Act: -0.0000

Data Index: 931786 (The Pile)

Max Activating Token Index: 118

Text #3

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.4421. Min Act: -0.0000

Data Index: 790425 (The Pile)

Max Activating Token Index: 46

Text #4

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.4729. Min Act: -0.0000

Data Index: 1900050 (The Pile)

Max Activating Token Index: 104

Text #5

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.4123. Min Act: -0.0000

Data Index: 976481 (The Pile)

Max Activating Token Index: 244

Text #6

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3829. Min Act: -0.0000

Data Index: 413847 (The Pile)

Max Activating Token Index: 755

Text #7

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.4377. Min Act: -0.0000

Data Index: 1212993 (The Pile)

Max Activating Token Index: 591

Text #8

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3862. Min Act: -0.0000

Data Index: 474716 (The Pile)

Max Activating Token Index: 193

Text #9

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.4098. Min Act: -0.0000

Data Index: 977168 (The Pile)

Max Activating Token Index: 946

Text #10

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3658. Min Act: -0.0000

Data Index: 1773634 (The Pile)

Max Activating Token Index: 776

Text #11

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.4328. Min Act: -0.0000

Data Index: 1901341 (The Pile)

Max Activating Token Index: 844

Text #12

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1950833 (The Pile)

Max Activating Token Index: 900

Text #13

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3385. Min Act: -0.0000

Data Index: 625044 (The Pile)

Max Activating Token Index: 672

Text #14

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3558. Min Act: -0.0000

Data Index: 1441617 (The Pile)

Max Activating Token Index: 646

Text #15

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3500. Min Act: -0.0000

Data Index: 1080753 (The Pile)

Max Activating Token Index: 492

Text #16

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3191. Min Act: -0.0000

Data Index: 522545 (The Pile)

Max Activating Token Index: 853

Text #17

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3770. Min Act: -0.0000

Data Index: 1217224 (The Pile)

Max Activating Token Index: 706

Text #18

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3402. Min Act: -0.0000

Data Index: 738786 (The Pile)

Max Activating Token Index: 471

Text #19

Max Range: 0.5071. Min Range: -0.5071

Max Act: 0.3332. Min Act: -0.0000

Data Index: 151610 (The Pile)

Max Activating Token Index: 21