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

Dataset: The Pile

Neuron 3104 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: 1.6488. Min Range: -1.6488

Max Act: 1.5876. Min Act: -0.0000

Data Index: 1673678 (The Pile)

Max Activating Token Index: 773

Text #1

Max Range: 1.6488. Min Range: -1.6488

Max Act: 1.6488. Min Act: -0.0000

Data Index: 1401795 (The Pile)

Max Activating Token Index: 705

Text #2

Max Range: 1.6488. Min Range: -1.6488

Max Act: 1.5880. Min Act: -0.0000

Data Index: 1772125 (The Pile)

Max Activating Token Index: 839

Text #3

Max Range: 1.6488. Min Range: -1.6488

Max Act: 1.5947. Min Act: -0.0000

Data Index: 283814 (The Pile)

Max Activating Token Index: 878

Text #4

Max Range: 1.6488. Min Range: -1.6488

Max Act: 1.5145. Min Act: -0.0000

Data Index: 739796 (The Pile)

Max Activating Token Index: 745

Text #5

Max Range: 1.6488. Min Range: -1.6488

Max Act: 1.5364. Min Act: -0.0000

Data Index: 256957 (The Pile)

Max Activating Token Index: 514

Text #6

Max Range: 1.6488. Min Range: -1.6488

Max Act: 1.4471. Min Act: -0.0000

Data Index: 394522 (The Pile)

Max Activating Token Index: 776

Text #7

Max Range: 1.6488. Min Range: -1.6488

Max Act: 1.4114. Min Act: -0.0000

Data Index: 1188223 (The Pile)

Max Activating Token Index: 904

Text #8

Max Range: 1.6488. Min Range: -1.6488

Max Act: 1.5043. Min Act: -0.0000

Data Index: 1523033 (The Pile)

Max Activating Token Index: 817

Text #9

Max Range: 1.6488. Min Range: -1.6488

Max Act: 1.5052. Min Act: -0.0000

Data Index: 680049 (The Pile)

Max Activating Token Index: 763

Text #10

Max Range: 1.6488. Min Range: -1.6488

Max Act: 1.4210. Min Act: -0.0000

Data Index: 819462 (The Pile)

Max Activating Token Index: 777

Text #11

Max Range: 1.6488. Min Range: -1.6488

Max Act: 1.3691. Min Act: -0.0000

Data Index: 331776 (The Pile)

Max Activating Token Index: 918

Text #12

Max Range: 1.6488. Min Range: -1.6488

Max Act: 1.4940. Min Act: -0.0000

Data Index: 40730 (The Pile)

Max Activating Token Index: 923

Text #13

Max Range: 1.6488. Min Range: -1.6488

Max Act: 1.4893. Min Act: -0.0000

Data Index: 556762 (The Pile)

Max Activating Token Index: 938

Text #14

Max Range: 1.6488. Min Range: -1.6488

Max Act: 1.4792. Min Act: -0.0000

Data Index: 1199619 (The Pile)

Max Activating Token Index: 594

Text #15

Max Range: 1.6488. Min Range: -1.6488

Max Act: 1.4609. Min Act: -0.0000

Data Index: 896603 (The Pile)

Max Activating Token Index: 686

Text #16

Max Range: 1.6488. Min Range: -1.6488

Max Act: 1.4418. Min Act: -0.0000

Data Index: 535710 (The Pile)

Max Activating Token Index: 546

Text #17

Max Range: 1.6488. Min Range: -1.6488

Max Act: 1.3414. Min Act: -0.0000

Data Index: 1708074 (The Pile)

Max Activating Token Index: 675

Text #18

Max Range: 1.6488. Min Range: -1.6488

Max Act: 1.4354. Min Act: -0.0000

Data Index: 889589 (The Pile)

Max Activating Token Index: 791

Text #19

Max Range: 1.6488. Min Range: -1.6488

Max Act: 1.4266. Min Act: -0.0000

Data Index: 1473735 (The Pile)

Max Activating Token Index: 686