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

Dataset: The Pile

Neuron 2397 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: 0.2642. Min Range: -0.2642

Max Act: 0.2642. Min Act: -0.0000

Data Index: 232117 (The Pile)

Max Activating Token Index: 687

Text #1

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.2329. Min Act: -0.0000

Data Index: 957891 (The Pile)

Max Activating Token Index: 1012

Text #2

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1967. Min Act: -0.0000

Data Index: 309306 (The Pile)

Max Activating Token Index: 592

Text #3

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1633. Min Act: -0.0000

Data Index: 1712416 (The Pile)

Max Activating Token Index: 418

Text #4

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1855. Min Act: -0.0000

Data Index: 634873 (The Pile)

Max Activating Token Index: 931

Text #5

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1678. Min Act: -0.0000

Data Index: 726476 (The Pile)

Max Activating Token Index: 954

Text #6

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1651. Min Act: -0.0000

Data Index: 1750927 (The Pile)

Max Activating Token Index: 386

Text #7

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1667605 (The Pile)

Max Activating Token Index: 327

Text #8

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1699. Min Act: -0.0000

Data Index: 1299050 (The Pile)

Max Activating Token Index: 996

Text #9

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1598. Min Act: -0.0000

Data Index: 1197964 (The Pile)

Max Activating Token Index: 964

Text #10

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1536. Min Act: -0.0000

Data Index: 1715015 (The Pile)

Max Activating Token Index: 824

Text #11

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1637. Min Act: -0.0000

Data Index: 74223 (The Pile)

Max Activating Token Index: 353

Text #12

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1696. Min Act: -0.0000

Data Index: 294399 (The Pile)

Max Activating Token Index: 831

Text #13

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1546. Min Act: -0.0000

Data Index: 636698 (The Pile)

Max Activating Token Index: 830

Text #14

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1530. Min Act: -0.0000

Data Index: 870424 (The Pile)

Max Activating Token Index: 770

Text #15

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1466. Min Act: -0.0000

Data Index: 1578605 (The Pile)

Max Activating Token Index: 683

Text #16

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1678. Min Act: -0.0000

Data Index: 1222839 (The Pile)

Max Activating Token Index: 759

Text #17

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1438. Min Act: -0.0000

Data Index: 895776 (The Pile)

Max Activating Token Index: 717

Text #18

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1408. Min Act: -0.0000

Data Index: 1410761 (The Pile)

Max Activating Token Index: 994

Text #19

Max Range: 0.2642. Min Range: -0.2642

Max Act: 0.1487. Min Act: -0.0000

Data Index: 1117653 (The Pile)

Max Activating Token Index: 974