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

Dataset: The Pile

Neuron 1039 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3996. Min Act: -0.0000

Data Index: 1139697 (The Pile)

Max Activating Token Index: 839

Text #1

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3799. Min Act: 0.0000

Data Index: 719914 (The Pile)

Max Activating Token Index: 866

Text #2

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3574. Min Act: -0.0000

Data Index: 1502036 (The Pile)

Max Activating Token Index: 464

Text #3

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3336. Min Act: -0.0000

Data Index: 498881 (The Pile)

Max Activating Token Index: 736

Text #4

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3277. Min Act: -0.0000

Data Index: 371607 (The Pile)

Max Activating Token Index: 1013

Text #5

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3268. Min Act: 0.0000

Data Index: 1199169 (The Pile)

Max Activating Token Index: 915

Text #6

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3159. Min Act: 0.0000

Data Index: 1797500 (The Pile)

Max Activating Token Index: 497

Text #7

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2971. Min Act: 0.0000

Data Index: 244521 (The Pile)

Max Activating Token Index: 498

Text #8

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2964. Min Act: -0.0000

Data Index: 1158477 (The Pile)

Max Activating Token Index: 617

Text #9

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2895. Min Act: -0.0000

Data Index: 1643126 (The Pile)

Max Activating Token Index: 675

Text #10

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2940. Min Act: 0.0000

Data Index: 1334859 (The Pile)

Max Activating Token Index: 984

Text #11

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2988. Min Act: -0.0000

Data Index: 811567 (The Pile)

Max Activating Token Index: 107

Text #12

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2992. Min Act: -0.0000

Data Index: 1766614 (The Pile)

Max Activating Token Index: 565

Text #13

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2860. Min Act: 0.0001

Data Index: 552058 (The Pile)

Max Activating Token Index: 329

Text #14

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3024. Min Act: -0.0000

Data Index: 1107911 (The Pile)

Max Activating Token Index: 343

Text #15

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2811. Min Act: -0.0000

Data Index: 236290 (The Pile)

Max Activating Token Index: 910

Text #16

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1231481 (The Pile)

Max Activating Token Index: 974

Text #17

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2724. Min Act: -0.0000

Data Index: 19960 (The Pile)

Max Activating Token Index: 948

Text #18

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2743. Min Act: -0.0000

Data Index: 960868 (The Pile)

Max Activating Token Index: 91

Text #19

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2945. Min Act: -0.0000

Data Index: 757586 (The Pile)

Max Activating Token Index: 271