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

Dataset: The Pile

Neuron 3779 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: 0.5864. Min Range: -0.5864

Max Act: 0.5441. Min Act: -0.0000

Data Index: 1366486 (The Pile)

Max Activating Token Index: 771

Text #1

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.5559. Min Act: -0.0000

Data Index: 1883406 (The Pile)

Max Activating Token Index: 780

Text #2

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1125377 (The Pile)

Max Activating Token Index: 394

Text #3

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1521568 (The Pile)

Max Activating Token Index: 485

Text #4

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.5419. Min Act: -0.0000

Data Index: 1721462 (The Pile)

Max Activating Token Index: 461

Text #5

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.5469. Min Act: -0.0000

Data Index: 1971987 (The Pile)

Max Activating Token Index: 604

Text #6

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.5434. Min Act: -0.0000

Data Index: 1408599 (The Pile)

Max Activating Token Index: 557

Text #7

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.5551. Min Act: -0.0000

Data Index: 762196 (The Pile)

Max Activating Token Index: 103

Text #8

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.5052. Min Act: -0.0000

Data Index: 1441551 (The Pile)

Max Activating Token Index: 376

Text #9

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.5121. Min Act: -0.0000

Data Index: 1701051 (The Pile)

Max Activating Token Index: 386

Text #10

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.5204. Min Act: -0.0000

Data Index: 136273 (The Pile)

Max Activating Token Index: 340

Text #11

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4786. Min Act: -0.0000

Data Index: 820350 (The Pile)

Max Activating Token Index: 141

Text #12

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4930. Min Act: -0.0000

Data Index: 321576 (The Pile)

Max Activating Token Index: 771

Text #13

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4626. Min Act: -0.0000

Data Index: 1952680 (The Pile)

Max Activating Token Index: 640

Text #14

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4838. Min Act: -0.0000

Data Index: 393789 (The Pile)

Max Activating Token Index: 844

Text #15

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4770. Min Act: -0.0000

Data Index: 734087 (The Pile)

Max Activating Token Index: 278

Text #16

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4892. Min Act: -0.0000

Data Index: 1727127 (The Pile)

Max Activating Token Index: 746

Text #17

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4745. Min Act: -0.0000

Data Index: 908310 (The Pile)

Max Activating Token Index: 603

Text #18

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4600. Min Act: -0.0000

Data Index: 1461517 (The Pile)

Max Activating Token Index: 315

Text #19

Max Range: 0.5864. Min Range: -0.5864

Max Act: 0.4260. Min Act: -0.0000

Data Index: 1683347 (The Pile)

Max Activating Token Index: 959