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

Dataset: The Pile

Neuron 3746 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.6900. Min Act: -0.0000

Data Index: 1422396 (The Pile)

Max Activating Token Index: 969

Text #1

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.6313. Min Act: -0.0000

Data Index: 1294000 (The Pile)

Max Activating Token Index: 930

Text #2

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.6489. Min Act: -0.0000

Data Index: 1129004 (The Pile)

Max Activating Token Index: 72

Text #3

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.6345. Min Act: -0.0000

Data Index: 775976 (The Pile)

Max Activating Token Index: 576

Text #4

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.6043. Min Act: -0.0000

Data Index: 414456 (The Pile)

Max Activating Token Index: 559

Text #5

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.6166. Min Act: -0.0000

Data Index: 1061333 (The Pile)

Max Activating Token Index: 624

Text #6

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.6276. Min Act: -0.0000

Data Index: 1372598 (The Pile)

Max Activating Token Index: 868

Text #7

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.5952. Min Act: -0.0000

Data Index: 1997407 (The Pile)

Max Activating Token Index: 991

Text #8

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.5873. Min Act: -0.0000

Data Index: 821793 (The Pile)

Max Activating Token Index: 961

Text #9

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.6373. Min Act: -0.0000

Data Index: 574334 (The Pile)

Max Activating Token Index: 212

Text #10

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.5815. Min Act: -0.0000

Data Index: 429925 (The Pile)

Max Activating Token Index: 692

Text #11

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.6072. Min Act: -0.0000

Data Index: 563781 (The Pile)

Max Activating Token Index: 648

Text #12

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.6241. Min Act: -0.0000

Data Index: 15802 (The Pile)

Max Activating Token Index: 294

Text #13

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.6008. Min Act: -0.0000

Data Index: 927437 (The Pile)

Max Activating Token Index: 386

Text #14

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.5976. Min Act: -0.0000

Data Index: 58094 (The Pile)

Max Activating Token Index: 665

Text #15

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.5943. Min Act: -0.0000

Data Index: 854678 (The Pile)

Max Activating Token Index: 918

Text #16

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.5774. Min Act: -0.0000

Data Index: 109341 (The Pile)

Max Activating Token Index: 899

Text #17

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1665079 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.5658. Min Act: -0.0000

Data Index: 549939 (The Pile)

Max Activating Token Index: 782

Text #19

Max Range: 0.6900. Min Range: -0.6900

Max Act: 0.5608. Min Act: -0.0000

Data Index: 962837 (The Pile)

Max Activating Token Index: 693