Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2593 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0033. Min Act: -0.0001

Data Index: 1289137 (The Pile)

Max Activating Token Index: 754

Text #1

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0033. Min Act: -0.0000

Data Index: 806336 (The Pile)

Max Activating Token Index: 700

Text #2

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0032. Min Act: -0.0000

Data Index: 1958530 (The Pile)

Max Activating Token Index: 778

Text #3

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0032. Min Act: -0.0001

Data Index: 895844 (The Pile)

Max Activating Token Index: 687

Text #4

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0031. Min Act: -0.0000

Data Index: 1889918 (The Pile)

Max Activating Token Index: 655

Text #5

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0031. Min Act: -0.0001

Data Index: 1308607 (The Pile)

Max Activating Token Index: 676

Text #6

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0030. Min Act: -0.0000

Data Index: 996242 (The Pile)

Max Activating Token Index: 687

Text #7

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0030. Min Act: -0.0001

Data Index: 1073651 (The Pile)

Max Activating Token Index: 694

Text #8

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0000

Data Index: 608327 (The Pile)

Max Activating Token Index: 777

Text #9

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0001

Data Index: 1058841 (The Pile)

Max Activating Token Index: 731

Text #10

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0000

Data Index: 414518 (The Pile)

Max Activating Token Index: 624

Text #11

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0001

Data Index: 1673997 (The Pile)

Max Activating Token Index: 711

Text #12

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0000

Data Index: 1534233 (The Pile)

Max Activating Token Index: 719

Text #13

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0001

Data Index: 676010 (The Pile)

Max Activating Token Index: 666

Text #14

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0000

Data Index: 963830 (The Pile)

Max Activating Token Index: 692

Text #15

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0001

Data Index: 464685 (The Pile)

Max Activating Token Index: 716

Text #16

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0001

Data Index: 172045 (The Pile)

Max Activating Token Index: 702

Text #17

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0001

Data Index: 1473161 (The Pile)

Max Activating Token Index: 718

Text #18

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0028. Min Act: -0.0001

Data Index: 1905151 (The Pile)

Max Activating Token Index: 701

Text #19

Max Range: 0.0033. Min Range: -0.0033

Max Act: 0.0029. Min Act: -0.0001

Data Index: 983673 (The Pile)

Max Activating Token Index: 761