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

Dataset: The Pile

Neuron 2460 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: 3.1315. Min Range: -3.1315

Max Act: 3.1315. Min Act: -0.0000

Data Index: 1504852 (The Pile)

Max Activating Token Index: 377

Text #1

Max Range: 3.1315. Min Range: -3.1315

Max Act: 2.7116. Min Act: -0.0000

Data Index: 1841983 (The Pile)

Max Activating Token Index: 415

Text #2

Max Range: 3.1315. Min Range: -3.1315

Max Act: 2.3503. Min Act: -0.0000

Data Index: 1618175 (The Pile)

Max Activating Token Index: 397

Text #3

Max Range: 3.1315. Min Range: -3.1315

Max Act: 2.5918. Min Act: -0.0000

Data Index: 1725224 (The Pile)

Max Activating Token Index: 666

Text #4

Max Range: 3.1315. Min Range: -3.1315

Max Act: 2.5562. Min Act: -0.0000

Data Index: 1668704 (The Pile)

Max Activating Token Index: 982

Text #5

Max Range: 3.1315. Min Range: -3.1315

Max Act: 2.2756. Min Act: -0.0000

Data Index: 761630 (The Pile)

Max Activating Token Index: 40

Text #6

Max Range: 3.1315. Min Range: -3.1315

Max Act: 2.5378. Min Act: -0.0000

Data Index: 939909 (The Pile)

Max Activating Token Index: 742

Text #7

Max Range: 3.1315. Min Range: -3.1315

Max Act: 2.1811. Min Act: -0.0000

Data Index: 925806 (The Pile)

Max Activating Token Index: 530

Text #8

Max Range: 3.1315. Min Range: -3.1315

Max Act: 2.5026. Min Act: -0.0000

Data Index: 342970 (The Pile)

Max Activating Token Index: 680

Text #9

Max Range: 3.1315. Min Range: -3.1315

Max Act: 2.3640. Min Act: -0.0000

Data Index: 1090696 (The Pile)

Max Activating Token Index: 701

Text #10

Max Range: 3.1315. Min Range: -3.1315

Max Act: 2.3614. Min Act: -0.0000

Data Index: 683898 (The Pile)

Max Activating Token Index: 496

Text #11

Max Range: 3.1315. Min Range: -3.1315

Max Act: 2.4972. Min Act: -0.0000

Data Index: 401062 (The Pile)

Max Activating Token Index: 276

Text #12

Max Range: 3.1315. Min Range: -3.1315

Max Act: 2.4623. Min Act: -0.0000

Data Index: 1385764 (The Pile)

Max Activating Token Index: 396

Text #13

Max Range: 3.1315. Min Range: -3.1315

Max Act: 2.1120. Min Act: -0.0000

Data Index: 832677 (The Pile)

Max Activating Token Index: 902

Text #14

Max Range: 3.1315. Min Range: -3.1315

Max Act: 2.3465. Min Act: -0.0000

Data Index: 109661 (The Pile)

Max Activating Token Index: 668

Text #15

Max Range: 3.1315. Min Range: -3.1315

Max Act: 2.3046. Min Act: -0.0000

Data Index: 321054 (The Pile)

Max Activating Token Index: 465

Text #16

Max Range: 3.1315. Min Range: -3.1315

Max Act: 2.4085. Min Act: -0.0000

Data Index: 783706 (The Pile)

Max Activating Token Index: 539

Text #17

Max Range: 3.1315. Min Range: -3.1315

Max Act: 2.3907. Min Act: -0.0000

Data Index: 1030398 (The Pile)

Max Activating Token Index: 224

Text #18

Max Range: 3.1315. Min Range: -3.1315

Max Act: 2.0408. Min Act: -0.0000

Data Index: 522010 (The Pile)

Max Activating Token Index: 627

Text #19

Max Range: 3.1315. Min Range: -3.1315

Max Act: 2.2959. Min Act: -0.0000

Data Index: 131450 (The Pile)

Max Activating Token Index: 679