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

Dataset: The Pile

Neuron 2693 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: 1.5981. Min Range: -1.5981

Max Act: 1.5981. Min Act: -0.0000

Data Index: 428642 (The Pile)

Max Activating Token Index: 620

Text #1

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.4966. Min Act: -0.0000

Data Index: 852621 (The Pile)

Max Activating Token Index: 638

Text #2

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.3614. Min Act: -0.0000

Data Index: 545796 (The Pile)

Max Activating Token Index: 810

Text #3

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.3969. Min Act: -0.0000

Data Index: 1084558 (The Pile)

Max Activating Token Index: 523

Text #4

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.3245. Min Act: -0.0000

Data Index: 1420602 (The Pile)

Max Activating Token Index: 775

Text #5

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.5663. Min Act: -0.0000

Data Index: 828851 (The Pile)

Max Activating Token Index: 512

Text #6

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2982. Min Act: -0.0000

Data Index: 1872244 (The Pile)

Max Activating Token Index: 299

Text #7

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2995. Min Act: -0.0000

Data Index: 1408649 (The Pile)

Max Activating Token Index: 180

Text #8

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.4322. Min Act: -0.0000

Data Index: 1429405 (The Pile)

Max Activating Token Index: 86

Text #9

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2566. Min Act: -0.0000

Data Index: 1231265 (The Pile)

Max Activating Token Index: 940

Text #10

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2728. Min Act: -0.0000

Data Index: 1241468 (The Pile)

Max Activating Token Index: 430

Text #11

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2743. Min Act: -0.0000

Data Index: 1267753 (The Pile)

Max Activating Token Index: 961

Text #12

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.3934. Min Act: -0.0000

Data Index: 279623 (The Pile)

Max Activating Token Index: 765

Text #13

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.3054. Min Act: -0.0000

Data Index: 1418356 (The Pile)

Max Activating Token Index: 446

Text #14

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.3321. Min Act: -0.0000

Data Index: 1636466 (The Pile)

Max Activating Token Index: 548

Text #15

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2950. Min Act: -0.0000

Data Index: 967009 (The Pile)

Max Activating Token Index: 392

Text #16

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2919. Min Act: -0.0000

Data Index: 1298498 (The Pile)

Max Activating Token Index: 178

Text #17

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2902. Min Act: -0.0000

Data Index: 982521 (The Pile)

Max Activating Token Index: 1003

Text #18

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2134. Min Act: -0.0000

Data Index: 884899 (The Pile)

Max Activating Token Index: 834

Text #19

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.3627. Min Act: -0.0000

Data Index: 1135364 (The Pile)

Max Activating Token Index: 154