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

Dataset: The Pile

Neuron 2084 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4635. Min Act: -0.0000

Data Index: 869520 (The Pile)

Max Activating Token Index: 850

Text #1

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4531. Min Act: -0.0000

Data Index: 1117687 (The Pile)

Max Activating Token Index: 26

Text #2

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1890086 (The Pile)

Max Activating Token Index: 377

Text #3

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4498. Min Act: -0.0000

Data Index: 1679685 (The Pile)

Max Activating Token Index: 116

Text #4

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3998. Min Act: -0.0000

Data Index: 1622676 (The Pile)

Max Activating Token Index: 608

Text #5

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3938. Min Act: -0.0000

Data Index: 1475022 (The Pile)

Max Activating Token Index: 472

Text #6

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4154. Min Act: -0.0000

Data Index: 1548126 (The Pile)

Max Activating Token Index: 53

Text #7

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4121. Min Act: -0.0000

Data Index: 357183 (The Pile)

Max Activating Token Index: 315

Text #8

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4041. Min Act: -0.0000

Data Index: 1838202 (The Pile)

Max Activating Token Index: 86

Text #9

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3647. Min Act: -0.0000

Data Index: 49442 (The Pile)

Max Activating Token Index: 408

Text #10

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3539. Min Act: -0.0000

Data Index: 1094864 (The Pile)

Max Activating Token Index: 779

Text #11

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3840. Min Act: -0.0000

Data Index: 1928580 (The Pile)

Max Activating Token Index: 104

Text #12

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3587. Min Act: -0.0000

Data Index: 1142996 (The Pile)

Max Activating Token Index: 860

Text #13

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3578. Min Act: -0.0000

Data Index: 806378 (The Pile)

Max Activating Token Index: 72

Text #14

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4031. Min Act: -0.0000

Data Index: 922751 (The Pile)

Max Activating Token Index: 160

Text #15

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1005584 (The Pile)

Max Activating Token Index: 543

Text #16

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3634. Min Act: -0.0000

Data Index: 630919 (The Pile)

Max Activating Token Index: 349

Text #17

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3756. Min Act: -0.0000

Data Index: 173939 (The Pile)

Max Activating Token Index: 397

Text #18

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.3843. Min Act: -0.0000

Data Index: 1431970 (The Pile)

Max Activating Token Index: 246

Text #19

Max Range: 0.4635. Min Range: -0.4635

Max Act: 0.4076. Min Act: -0.0000

Data Index: 988767 (The Pile)

Max Activating Token Index: 551