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

Dataset: The Pile

Neuron 781 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.3713. Min Act: -0.0000

Data Index: 747224 (The Pile)

Max Activating Token Index: 145

Text #1

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.2126. Min Act: -0.0000

Data Index: 543754 (The Pile)

Max Activating Token Index: 68

Text #2

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.3403. Min Act: -0.0000

Data Index: 1922990 (The Pile)

Max Activating Token Index: 782

Text #3

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.1903. Min Act: -0.0000

Data Index: 157331 (The Pile)

Max Activating Token Index: 154

Text #4

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.2198. Min Act: -0.0000

Data Index: 564770 (The Pile)

Max Activating Token Index: 348

Text #5

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.1684. Min Act: -0.0000

Data Index: 1985855 (The Pile)

Max Activating Token Index: 402

Text #6

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.1688. Min Act: -0.0000

Data Index: 1221014 (The Pile)

Max Activating Token Index: 981

Text #7

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.1716. Min Act: -0.0000

Data Index: 662334 (The Pile)

Max Activating Token Index: 349

Text #8

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.0231. Min Act: -0.0000

Data Index: 1694523 (The Pile)

Max Activating Token Index: 234

Text #9

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.0212. Min Act: -0.0000

Data Index: 1498882 (The Pile)

Max Activating Token Index: 837

Text #10

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.0741. Min Act: -0.0000

Data Index: 366005 (The Pile)

Max Activating Token Index: 789

Text #11

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.0093. Min Act: -0.0000

Data Index: 627524 (The Pile)

Max Activating Token Index: 124

Text #12

Max Range: 1.3713. Min Range: -1.3713

Max Act: 1.0095. Min Act: -0.0000

Data Index: 264620 (The Pile)

Max Activating Token Index: 515

Text #13

Max Range: 1.3713. Min Range: -1.3713

Max Act: 0.9003. Min Act: -0.0000

Data Index: 972956 (The Pile)

Max Activating Token Index: 447

Text #14

Max Range: 1.3713. Min Range: -1.3713

Max Act: 0.9896. Min Act: -0.0000

Data Index: 1358035 (The Pile)

Max Activating Token Index: 841

Text #15

Max Range: 1.3713. Min Range: -1.3713

Max Act: 0.9533. Min Act: -0.0000

Data Index: 937428 (The Pile)

Max Activating Token Index: 644

Text #16

Max Range: 1.3713. Min Range: -1.3713

Max Act: 0.9516. Min Act: -0.0000

Data Index: 596401 (The Pile)

Max Activating Token Index: 846

Text #17

Max Range: 1.3713. Min Range: -1.3713

Max Act: 0.9659. Min Act: -0.0000

Data Index: 513670 (The Pile)

Max Activating Token Index: 188

Text #18

Max Range: 1.3713. Min Range: -1.3713

Max Act: 0.9356. Min Act: -0.0000

Data Index: 733391 (The Pile)

Max Activating Token Index: 431

Text #19

Max Range: 1.3713. Min Range: -1.3713

Max Act: 0.9364. Min Act: -0.0000

Data Index: 698522 (The Pile)

Max Activating Token Index: 204