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

Dataset: The Pile

Neuron 4744 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: 0.1473. Min Range: -0.1473

Max Act: 0.1473. Min Act: -0.0000

Data Index: 626840 (The Pile)

Max Activating Token Index: 1008

Text #1

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1171. Min Act: -0.0000

Data Index: 1073652 (The Pile)

Max Activating Token Index: 945

Text #2

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1281. Min Act: -0.0000

Data Index: 1807462 (The Pile)

Max Activating Token Index: 927

Text #3

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0905. Min Act: -0.0000

Data Index: 1195107 (The Pile)

Max Activating Token Index: 917

Text #4

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.1011. Min Act: -0.0000

Data Index: 1697361 (The Pile)

Max Activating Token Index: 909

Text #5

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0993. Min Act: -0.0000

Data Index: 1260302 (The Pile)

Max Activating Token Index: 810

Text #6

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0938. Min Act: -0.0000

Data Index: 87770 (The Pile)

Max Activating Token Index: 926

Text #7

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0857. Min Act: -0.0000

Data Index: 1659452 (The Pile)

Max Activating Token Index: 999

Text #8

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0943. Min Act: -0.0000

Data Index: 289928 (The Pile)

Max Activating Token Index: 261

Text #9

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0935. Min Act: -0.0000

Data Index: 1397369 (The Pile)

Max Activating Token Index: 718

Text #10

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0867. Min Act: -0.0000

Data Index: 751766 (The Pile)

Max Activating Token Index: 714

Text #11

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1124201 (The Pile)

Max Activating Token Index: 860

Text #12

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0963. Min Act: -0.0000

Data Index: 1843674 (The Pile)

Max Activating Token Index: 258

Text #13

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0948. Min Act: -0.0000

Data Index: 292333 (The Pile)

Max Activating Token Index: 880

Text #14

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0901. Min Act: -0.0000

Data Index: 497748 (The Pile)

Max Activating Token Index: 992

Text #15

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0854. Min Act: -0.0000

Data Index: 1269402 (The Pile)

Max Activating Token Index: 877

Text #16

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0818. Min Act: -0.0000

Data Index: 1716959 (The Pile)

Max Activating Token Index: 791

Text #17

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0816. Min Act: -0.0000

Data Index: 1022806 (The Pile)

Max Activating Token Index: 550

Text #18

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0920. Min Act: -0.0000

Data Index: 1440400 (The Pile)

Max Activating Token Index: 769

Text #19

Max Range: 0.1473. Min Range: -0.1473

Max Act: 0.0811. Min Act: -0.0000

Data Index: 1983321 (The Pile)

Max Activating Token Index: 374