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

Dataset: The Pile

Neuron 4463 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: 0.5569. Min Range: -0.5569

Max Act: 0.5569. Min Act: -0.0000

Data Index: 281887 (The Pile)

Max Activating Token Index: 941

Text #1

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1580714 (The Pile)

Max Activating Token Index: 995

Text #2

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1363830 (The Pile)

Max Activating Token Index: 595

Text #3

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4618. Min Act: -0.0000

Data Index: 443100 (The Pile)

Max Activating Token Index: 912

Text #4

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1006103 (The Pile)

Max Activating Token Index: 902

Text #5

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.3385. Min Act: -0.0000

Data Index: 1314481 (The Pile)

Max Activating Token Index: 854

Text #6

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1052464 (The Pile)

Max Activating Token Index: 635

Text #7

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4067. Min Act: -0.0000

Data Index: 1379541 (The Pile)

Max Activating Token Index: 738

Text #8

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1969400 (The Pile)

Max Activating Token Index: 968

Text #9

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4244. Min Act: -0.0000

Data Index: 1489623 (The Pile)

Max Activating Token Index: 826

Text #10

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1090371 (The Pile)

Max Activating Token Index: 932

Text #11

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4146. Min Act: -0.0000

Data Index: 121483 (The Pile)

Max Activating Token Index: 761

Text #12

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.3968. Min Act: -0.0000

Data Index: 94748 (The Pile)

Max Activating Token Index: 585

Text #13

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4280. Min Act: -0.0000

Data Index: 154222 (The Pile)

Max Activating Token Index: 628

Text #14

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.2875. Min Act: -0.0000

Data Index: 902014 (The Pile)

Max Activating Token Index: 997

Text #15

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.3678. Min Act: -0.0000

Data Index: 321828 (The Pile)

Max Activating Token Index: 883

Text #16

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1075327 (The Pile)

Max Activating Token Index: 305

Text #17

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.3829. Min Act: -0.0000

Data Index: 1921113 (The Pile)

Max Activating Token Index: 999

Text #18

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.3948. Min Act: -0.0000

Data Index: 1563214 (The Pile)

Max Activating Token Index: 995

Text #19

Max Range: 0.5569. Min Range: -0.5569

Max Act: 0.4048. Min Act: -0.0000

Data Index: 592425 (The Pile)

Max Activating Token Index: 387