Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2326 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.6794. Min Act: -0.0000

Data Index: 1501415 (The Pile)

Max Activating Token Index: 600

Text #1

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.6346. Min Act: -0.0000

Data Index: 1873726 (The Pile)

Max Activating Token Index: 581

Text #2

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.6011. Min Act: -0.0000

Data Index: 314564 (The Pile)

Max Activating Token Index: 943

Text #3

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.5155. Min Act: -0.0000

Data Index: 1809011 (The Pile)

Max Activating Token Index: 875

Text #4

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.5144. Min Act: -0.0000

Data Index: 547408 (The Pile)

Max Activating Token Index: 60

Text #5

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.5097. Min Act: -0.0000

Data Index: 1047556 (The Pile)

Max Activating Token Index: 916

Text #6

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.4817. Min Act: -0.0000

Data Index: 562695 (The Pile)

Max Activating Token Index: 435

Text #7

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.4793. Min Act: -0.0000

Data Index: 726690 (The Pile)

Max Activating Token Index: 185

Text #8

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.4711. Min Act: -0.0000

Data Index: 1191663 (The Pile)

Max Activating Token Index: 386

Text #9

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.4790. Min Act: -0.0000

Data Index: 1741861 (The Pile)

Max Activating Token Index: 629

Text #10

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.4606. Min Act: -0.0000

Data Index: 975814 (The Pile)

Max Activating Token Index: 589

Text #11

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.4122. Min Act: -0.0000

Data Index: 1883636 (The Pile)

Max Activating Token Index: 846

Text #12

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.4703. Min Act: -0.0000

Data Index: 1836561 (The Pile)

Max Activating Token Index: 799

Text #13

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.4503. Min Act: -0.0000

Data Index: 894598 (The Pile)

Max Activating Token Index: 569

Text #14

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.4234. Min Act: -0.0000

Data Index: 77464 (The Pile)

Max Activating Token Index: 163

Text #15

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1628985 (The Pile)

Max Activating Token Index: 884

Text #16

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.4372. Min Act: -0.0000

Data Index: 680881 (The Pile)

Max Activating Token Index: 135

Text #17

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.4511. Min Act: -0.0000

Data Index: 685648 (The Pile)

Max Activating Token Index: 584

Text #18

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.4318. Min Act: -0.0000

Data Index: 1001671 (The Pile)

Max Activating Token Index: 441

Text #19

Max Range: 0.6794. Min Range: -0.6794

Max Act: 0.4298. Min Act: -0.0000

Data Index: 390391 (The Pile)

Max Activating Token Index: 764