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

Dataset: The Pile

Neuron 1513 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: 0.4982. Min Range: -0.4982

Max Act: 0.4516. Min Act: -0.0000

Data Index: 877189 (The Pile)

Max Activating Token Index: 941

Text #1

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1251256 (The Pile)

Max Activating Token Index: 688

Text #2

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.4982. Min Act: -0.0000

Data Index: 1477729 (The Pile)

Max Activating Token Index: 167

Text #3

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3892. Min Act: -0.0000

Data Index: 1641545 (The Pile)

Max Activating Token Index: 917

Text #4

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3483. Min Act: -0.0000

Data Index: 924798 (The Pile)

Max Activating Token Index: 891

Text #5

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3737. Min Act: -0.0000

Data Index: 543416 (The Pile)

Max Activating Token Index: 898

Text #6

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3741. Min Act: -0.0000

Data Index: 102674 (The Pile)

Max Activating Token Index: 979

Text #7

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3763. Min Act: -0.0000

Data Index: 1054396 (The Pile)

Max Activating Token Index: 474

Text #8

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3533. Min Act: -0.0000

Data Index: 1659328 (The Pile)

Max Activating Token Index: 496

Text #9

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3878. Min Act: -0.0000

Data Index: 1075256 (The Pile)

Max Activating Token Index: 937

Text #10

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3299. Min Act: -0.0000

Data Index: 247289 (The Pile)

Max Activating Token Index: 948

Text #11

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3107. Min Act: -0.0000

Data Index: 642260 (The Pile)

Max Activating Token Index: 775

Text #12

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3538. Min Act: -0.0000

Data Index: 1081944 (The Pile)

Max Activating Token Index: 574

Text #13

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3383. Min Act: -0.0000

Data Index: 1938163 (The Pile)

Max Activating Token Index: 819

Text #14

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3250. Min Act: -0.0000

Data Index: 3283 (The Pile)

Max Activating Token Index: 834

Text #15

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3357. Min Act: -0.0000

Data Index: 1754895 (The Pile)

Max Activating Token Index: 719

Text #16

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3260. Min Act: -0.0000

Data Index: 1975167 (The Pile)

Max Activating Token Index: 218

Text #17

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.2645. Min Act: -0.0000

Data Index: 201623 (The Pile)

Max Activating Token Index: 855

Text #18

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3450. Min Act: -0.0000

Data Index: 711405 (The Pile)

Max Activating Token Index: 399

Text #19

Max Range: 0.4982. Min Range: -0.4982

Max Act: 0.3233. Min Act: -0.0000

Data Index: 1235101 (The Pile)

Max Activating Token Index: 740