Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1025 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0729. Min Act: -0.0005

Data Index: 997574 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0725. Min Act: -0.0005

Data Index: 630739 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0698. Min Act: -0.0005

Data Index: 958463 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0696. Min Act: -0.0005

Data Index: 453687 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0650. Min Act: -0.0005

Data Index: 1186094 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0671. Min Act: -0.0005

Data Index: 456327 (C4 (Web Text))

Max Activating Token Index: 568

Text #6

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0642. Min Act: -0.0005

Data Index: 1122365 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0665. Min Act: -0.0005

Data Index: 96321 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0639. Min Act: -0.0005

Data Index: 1201142 (C4 (Web Text))

Max Activating Token Index: 78

Text #9

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0638. Min Act: -0.0005

Data Index: 840570 (C4 (Web Text))

Max Activating Token Index: 981

Text #10

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0642. Min Act: -0.0005

Data Index: 1110 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0609. Min Act: -0.0005

Data Index: 89652 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0626. Min Act: -0.0005

Data Index: 773193 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0647. Min Act: -0.0005

Data Index: 215636 (C4 (Web Text))

Max Activating Token Index: 485

Text #14

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0636. Min Act: -0.0005

Data Index: 957980 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0625. Min Act: -0.0005

Data Index: 215951 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0624. Min Act: -0.0005

Data Index: 962201 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0609. Min Act: -0.0005

Data Index: 229781 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0611. Min Act: -0.0005

Data Index: 807132 (C4 (Web Text))

Max Activating Token Index: 255

Text #19

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0607. Min Act: -0.0005

Data Index: 1358700 (C4 (Web Text))

Max Activating Token Index: 554