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

Dataset: The Pile

Neuron 3849 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: 0.7137. Min Range: -0.7137

Max Act: 0.7137. Min Act: -0.0000

Data Index: 1150876 (The Pile)

Max Activating Token Index: 748

Text #1

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.6747. Min Act: -0.0000

Data Index: 518646 (The Pile)

Max Activating Token Index: 231

Text #2

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5682. Min Act: -0.0000

Data Index: 1080131 (The Pile)

Max Activating Token Index: 596

Text #3

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1883901 (The Pile)

Max Activating Token Index: 1008

Text #4

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.4599. Min Act: -0.0000

Data Index: 306855 (The Pile)

Max Activating Token Index: 712

Text #5

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.6413. Min Act: -0.0000

Data Index: 1951070 (The Pile)

Max Activating Token Index: 960

Text #6

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5364. Min Act: -0.0000

Data Index: 1465621 (The Pile)

Max Activating Token Index: 507

Text #7

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5411. Min Act: -0.0000

Data Index: 459537 (The Pile)

Max Activating Token Index: 594

Text #8

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5266. Min Act: -0.0000

Data Index: 1217699 (The Pile)

Max Activating Token Index: 216

Text #9

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1168875 (The Pile)

Max Activating Token Index: 652

Text #10

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5481. Min Act: -0.0000

Data Index: 594110 (The Pile)

Max Activating Token Index: 577

Text #11

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5444. Min Act: -0.0000

Data Index: 447190 (The Pile)

Max Activating Token Index: 509

Text #12

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1819645 (The Pile)

Max Activating Token Index: 626

Text #13

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5987. Min Act: -0.0000

Data Index: 746721 (The Pile)

Max Activating Token Index: 550

Text #14

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1431613 (The Pile)

Max Activating Token Index: 292

Text #15

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.4719. Min Act: -0.0000

Data Index: 713417 (The Pile)

Max Activating Token Index: 972

Text #16

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.4210. Min Act: -0.0000

Data Index: 555987 (The Pile)

Max Activating Token Index: 917

Text #17

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.4958. Min Act: -0.0000

Data Index: 1501681 (The Pile)

Max Activating Token Index: 635

Text #18

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.4755. Min Act: -0.0000

Data Index: 49785 (The Pile)

Max Activating Token Index: 63

Text #19

Max Range: 0.7137. Min Range: -0.7137

Max Act: 0.5066. Min Act: -0.0000

Data Index: 777790 (The Pile)

Max Activating Token Index: 704