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

Dataset: The Pile

Neuron 4212 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: 1.5892. Min Range: -1.5892

Max Act: 1.5892. Min Act: -0.0000

Data Index: 1451212 (The Pile)

Max Activating Token Index: 863

Text #1

Max Range: 1.5892. Min Range: -1.5892

Max Act: 1.1265. Min Act: -0.0000

Data Index: 406031 (The Pile)

Max Activating Token Index: 170

Text #2

Max Range: 1.5892. Min Range: -1.5892

Max Act: 0.9462. Min Act: -0.0000

Data Index: 1235484 (The Pile)

Max Activating Token Index: 934

Text #3

Max Range: 1.5892. Min Range: -1.5892

Max Act: 0.9840. Min Act: -0.0000

Data Index: 1543113 (The Pile)

Max Activating Token Index: 609

Text #4

Max Range: 1.5892. Min Range: -1.5892

Max Act: 0.9056. Min Act: -0.0000

Data Index: 278010 (The Pile)

Max Activating Token Index: 168

Text #5

Max Range: 1.5892. Min Range: -1.5892

Max Act: 0.8011. Min Act: -0.0000

Data Index: 1707649 (The Pile)

Max Activating Token Index: 342

Text #6

Max Range: 1.5892. Min Range: -1.5892

Max Act: 0.8431. Min Act: -0.0000

Data Index: 237734 (The Pile)

Max Activating Token Index: 46

Text #7

Max Range: 1.5892. Min Range: -1.5892

Max Act: 0.8184. Min Act: -0.0000

Data Index: 682319 (The Pile)

Max Activating Token Index: 660

Text #8

Max Range: 1.5892. Min Range: -1.5892

Max Act: 0.8332. Min Act: -0.0000

Data Index: 1087855 (The Pile)

Max Activating Token Index: 715

Text #9

Max Range: 1.5892. Min Range: -1.5892

Max Act: 0.7883. Min Act: -0.0000

Data Index: 898163 (The Pile)

Max Activating Token Index: 865

Text #10

Max Range: 1.5892. Min Range: -1.5892

Max Act: 0.6333. Min Act: -0.0000

Data Index: 860274 (The Pile)

Max Activating Token Index: 595

Text #11

Max Range: 1.5892. Min Range: -1.5892

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1095877 (The Pile)

Max Activating Token Index: 612

Text #12

Max Range: 1.5892. Min Range: -1.5892

Max Act: 0.7403. Min Act: -0.0000

Data Index: 252679 (The Pile)

Max Activating Token Index: 229

Text #13

Max Range: 1.5892. Min Range: -1.5892

Max Act: 0.7453. Min Act: -0.0000

Data Index: 1335193 (The Pile)

Max Activating Token Index: 180

Text #14

Max Range: 1.5892. Min Range: -1.5892

Max Act: 0.7381. Min Act: -0.0000

Data Index: 1119111 (The Pile)

Max Activating Token Index: 934

Text #15

Max Range: 1.5892. Min Range: -1.5892

Max Act: 0.7293. Min Act: 0.0000

Data Index: 632621 (The Pile)

Max Activating Token Index: 453

Text #16

Max Range: 1.5892. Min Range: -1.5892

Max Act: 0.5920. Min Act: -0.0000

Data Index: 931994 (The Pile)

Max Activating Token Index: 964

Text #17

Max Range: 1.5892. Min Range: -1.5892

Max Act: 0.6719. Min Act: -0.0000

Data Index: 341320 (The Pile)

Max Activating Token Index: 367

Text #18

Max Range: 1.5892. Min Range: -1.5892

Max Act: 0.6990. Min Act: 0.0000

Data Index: 1909699 (The Pile)

Max Activating Token Index: 346

Text #19

Max Range: 1.5892. Min Range: -1.5892

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1862233 (The Pile)

Max Activating Token Index: 588