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

Dataset: The Pile

Neuron 4603 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0584. Min Act: 0.0000

Data Index: 1373332 (The Pile)

Max Activating Token Index: 891

Text #1

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0572. Min Act: -0.0000

Data Index: 821942 (The Pile)

Max Activating Token Index: 4

Text #2

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0572. Min Act: 0.0000

Data Index: 1409078 (The Pile)

Max Activating Token Index: 906

Text #3

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0541. Min Act: 0.0000

Data Index: 939889 (The Pile)

Max Activating Token Index: 372

Text #4

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0531. Min Act: 0.0000

Data Index: 1882018 (The Pile)

Max Activating Token Index: 405

Text #5

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0530. Min Act: -0.0000

Data Index: 1187969 (The Pile)

Max Activating Token Index: 131

Text #6

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0521. Min Act: -0.0000

Data Index: 1898042 (The Pile)

Max Activating Token Index: 908

Text #7

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0515. Min Act: -0.0000

Data Index: 826632 (The Pile)

Max Activating Token Index: 675

Text #8

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0511. Min Act: 0.0000

Data Index: 47938 (The Pile)

Max Activating Token Index: 987

Text #9

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0492. Min Act: -0.0000

Data Index: 1014560 (The Pile)

Max Activating Token Index: 15

Text #10

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0510. Min Act: -0.0000

Data Index: 95706 (The Pile)

Max Activating Token Index: 50

Text #11

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0509. Min Act: -0.0000

Data Index: 979400 (The Pile)

Max Activating Token Index: 846

Text #12

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0507. Min Act: -0.0000

Data Index: 37082 (The Pile)

Max Activating Token Index: 909

Text #13

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0507. Min Act: -0.0000

Data Index: 425968 (The Pile)

Max Activating Token Index: 5

Text #14

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0498. Min Act: 0.0000

Data Index: 443661 (The Pile)

Max Activating Token Index: 799

Text #15

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0493. Min Act: -0.0000

Data Index: 936996 (The Pile)

Max Activating Token Index: 864

Text #16

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0508. Min Act: 0.0000

Data Index: 845897 (The Pile)

Max Activating Token Index: 49

Text #17

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0489. Min Act: -0.0000

Data Index: 735156 (The Pile)

Max Activating Token Index: 1018

Text #18

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0505. Min Act: 0.0000

Data Index: 763856 (The Pile)

Max Activating Token Index: 948

Text #19

Max Range: 0.0584. Min Range: -0.0584

Max Act: 0.0489. Min Act: -0.0000

Data Index: 479230 (The Pile)

Max Activating Token Index: 126