Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2709 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0943. Min Act: -0.0000

Data Index: 319021 (The Pile)

Max Activating Token Index: 75

Text #1

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0749. Min Act: -0.0000

Data Index: 166454 (The Pile)

Max Activating Token Index: 660

Text #2

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0714. Min Act: -0.0000

Data Index: 693644 (The Pile)

Max Activating Token Index: 246

Text #3

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0712. Min Act: -0.0000

Data Index: 227710 (The Pile)

Max Activating Token Index: 360

Text #4

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0744. Min Act: -0.0000

Data Index: 1141574 (The Pile)

Max Activating Token Index: 172

Text #5

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0688. Min Act: -0.0000

Data Index: 1974706 (The Pile)

Max Activating Token Index: 100

Text #6

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0679. Min Act: -0.0000

Data Index: 1814314 (The Pile)

Max Activating Token Index: 35

Text #7

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0660. Min Act: -0.0000

Data Index: 498582 (The Pile)

Max Activating Token Index: 335

Text #8

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0658. Min Act: -0.0000

Data Index: 1884423 (The Pile)

Max Activating Token Index: 667

Text #9

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0666. Min Act: -0.0000

Data Index: 1915674 (The Pile)

Max Activating Token Index: 292

Text #10

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0659. Min Act: -0.0000

Data Index: 765657 (The Pile)

Max Activating Token Index: 900

Text #11

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0656. Min Act: -0.0000

Data Index: 1813050 (The Pile)

Max Activating Token Index: 430

Text #12

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0602. Min Act: -0.0000

Data Index: 794230 (The Pile)

Max Activating Token Index: 539

Text #13

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0633. Min Act: -0.0000

Data Index: 1955738 (The Pile)

Max Activating Token Index: 612

Text #14

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0618. Min Act: -0.0000

Data Index: 1301343 (The Pile)

Max Activating Token Index: 1013

Text #15

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0589. Min Act: -0.0000

Data Index: 1462928 (The Pile)

Max Activating Token Index: 77

Text #16

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0587. Min Act: -0.0000

Data Index: 478998 (The Pile)

Max Activating Token Index: 62

Text #17

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0586. Min Act: -0.0000

Data Index: 1996329 (The Pile)

Max Activating Token Index: 33

Text #18

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0583. Min Act: -0.0000

Data Index: 324219 (The Pile)

Max Activating Token Index: 1000

Text #19

Max Range: 0.0943. Min Range: -0.0943

Max Act: 0.0626. Min Act: -0.0000

Data Index: 1787676 (The Pile)

Max Activating Token Index: 511