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

Dataset: The Pile

Neuron 1655 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.1147. Min Act: -0.0000

Data Index: 1573703 (The Pile)

Max Activating Token Index: 825

Text #1

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0715. Min Act: -0.0000

Data Index: 859866 (The Pile)

Max Activating Token Index: 176

Text #2

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0717. Min Act: -0.0000

Data Index: 1093179 (The Pile)

Max Activating Token Index: 857

Text #3

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0614. Min Act: -0.0000

Data Index: 793952 (The Pile)

Max Activating Token Index: 558

Text #4

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0645. Min Act: -0.0000

Data Index: 795468 (The Pile)

Max Activating Token Index: 440

Text #5

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0625. Min Act: -0.0000

Data Index: 534098 (The Pile)

Max Activating Token Index: 623

Text #6

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0623. Min Act: -0.0000

Data Index: 1242193 (The Pile)

Max Activating Token Index: 591

Text #7

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0648. Min Act: -0.0000

Data Index: 1710296 (The Pile)

Max Activating Token Index: 500

Text #8

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0667. Min Act: -0.0000

Data Index: 1722018 (The Pile)

Max Activating Token Index: 103

Text #9

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0606. Min Act: -0.0000

Data Index: 410966 (The Pile)

Max Activating Token Index: 384

Text #10

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0596. Min Act: -0.0000

Data Index: 1715415 (The Pile)

Max Activating Token Index: 632

Text #11

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0617. Min Act: -0.0000

Data Index: 1303162 (The Pile)

Max Activating Token Index: 570

Text #12

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0587. Min Act: -0.0000

Data Index: 1249599 (The Pile)

Max Activating Token Index: 155

Text #13

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0614. Min Act: -0.0000

Data Index: 1042193 (The Pile)

Max Activating Token Index: 932

Text #14

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0652. Min Act: -0.0000

Data Index: 225832 (The Pile)

Max Activating Token Index: 250

Text #15

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0598. Min Act: -0.0000

Data Index: 1678976 (The Pile)

Max Activating Token Index: 984

Text #16

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0599. Min Act: -0.0000

Data Index: 385398 (The Pile)

Max Activating Token Index: 484

Text #17

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0562. Min Act: -0.0000

Data Index: 1788320 (The Pile)

Max Activating Token Index: 675

Text #18

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0571. Min Act: -0.0000

Data Index: 984318 (The Pile)

Max Activating Token Index: 304

Text #19

Max Range: 0.1147. Min Range: -0.1147

Max Act: 0.0589. Min Act: -0.0000

Data Index: 706601 (The Pile)

Max Activating Token Index: 535