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

Dataset: The Pile

Neuron 3687 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: 0.1021. Min Range: -0.1021

Max Act: 0.1021. Min Act: -0.0000

Data Index: 1824294 (The Pile)

Max Activating Token Index: 904

Text #1

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0944. Min Act: -0.0000

Data Index: 626612 (The Pile)

Max Activating Token Index: 887

Text #2

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0938. Min Act: -0.0000

Data Index: 1701087 (The Pile)

Max Activating Token Index: 398

Text #3

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0910. Min Act: -0.0001

Data Index: 88800 (The Pile)

Max Activating Token Index: 232

Text #4

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0838. Min Act: -0.0000

Data Index: 864333 (The Pile)

Max Activating Token Index: 509

Text #5

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0797. Min Act: -0.0000

Data Index: 681285 (The Pile)

Max Activating Token Index: 62

Text #6

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0778. Min Act: -0.0000

Data Index: 1853088 (The Pile)

Max Activating Token Index: 253

Text #7

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0792. Min Act: -0.0000

Data Index: 235050 (The Pile)

Max Activating Token Index: 699

Text #8

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0734. Min Act: -0.0000

Data Index: 350822 (The Pile)

Max Activating Token Index: 41

Text #9

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0737. Min Act: -0.0000

Data Index: 1304955 (The Pile)

Max Activating Token Index: 235

Text #10

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0762. Min Act: -0.0000

Data Index: 957740 (The Pile)

Max Activating Token Index: 462

Text #11

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0733. Min Act: -0.0000

Data Index: 1975593 (The Pile)

Max Activating Token Index: 68

Text #12

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0655. Min Act: -0.0000

Data Index: 179163 (The Pile)

Max Activating Token Index: 988

Text #13

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0723. Min Act: -0.0000

Data Index: 1000575 (The Pile)

Max Activating Token Index: 498

Text #14

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0721. Min Act: -0.0000

Data Index: 992536 (The Pile)

Max Activating Token Index: 516

Text #15

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0716. Min Act: -0.0000

Data Index: 1805366 (The Pile)

Max Activating Token Index: 411

Text #16

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0707. Min Act: -0.0000

Data Index: 113680 (The Pile)

Max Activating Token Index: 382

Text #17

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0676. Min Act: -0.0000

Data Index: 1229023 (The Pile)

Max Activating Token Index: 522

Text #18

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0653. Min Act: -0.0000

Data Index: 47897 (The Pile)

Max Activating Token Index: 578

Text #19

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0703. Min Act: -0.0000

Data Index: 820746 (The Pile)

Max Activating Token Index: 686