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

Dataset: The Pile

Neuron 4859 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: 5.7467. Min Range: -5.7467

Max Act: 5.7467. Min Act: -0.0000

Data Index: 1879528 (The Pile)

Max Activating Token Index: 231

Text #1

Max Range: 5.7467. Min Range: -5.7467

Max Act: 5.7099. Min Act: -0.0000

Data Index: 1203353 (The Pile)

Max Activating Token Index: 247

Text #2

Max Range: 5.7467. Min Range: -5.7467

Max Act: 5.3072. Min Act: -0.0000

Data Index: 691629 (The Pile)

Max Activating Token Index: 420

Text #3

Max Range: 5.7467. Min Range: -5.7467

Max Act: 5.5717. Min Act: -0.0000

Data Index: 1412554 (The Pile)

Max Activating Token Index: 188

Text #4

Max Range: 5.7467. Min Range: -5.7467

Max Act: 5.3992. Min Act: -0.0000

Data Index: 913126 (The Pile)

Max Activating Token Index: 884

Text #5

Max Range: 5.7467. Min Range: -5.7467

Max Act: 5.2589. Min Act: -0.0000

Data Index: 1756883 (The Pile)

Max Activating Token Index: 765

Text #6

Max Range: 5.7467. Min Range: -5.7467

Max Act: 5.3229. Min Act: -0.0000

Data Index: 1823596 (The Pile)

Max Activating Token Index: 246

Text #7

Max Range: 5.7467. Min Range: -5.7467

Max Act: 4.8869. Min Act: -0.0000

Data Index: 1590448 (The Pile)

Max Activating Token Index: 624

Text #8

Max Range: 5.7467. Min Range: -5.7467

Max Act: 4.2660. Min Act: -0.0000

Data Index: 1313242 (The Pile)

Max Activating Token Index: 909

Text #9

Max Range: 5.7467. Min Range: -5.7467

Max Act: 4.9603. Min Act: -0.0000

Data Index: 1627796 (The Pile)

Max Activating Token Index: 110

Text #10

Max Range: 5.7467. Min Range: -5.7467

Max Act: 5.1015. Min Act: -0.0000

Data Index: 798176 (The Pile)

Max Activating Token Index: 329

Text #11

Max Range: 5.7467. Min Range: -5.7467

Max Act: 4.5986. Min Act: -0.0000

Data Index: 1807992 (The Pile)

Max Activating Token Index: 749

Text #12

Max Range: 5.7467. Min Range: -5.7467

Max Act: 5.2711. Min Act: -0.0000

Data Index: 1232999 (The Pile)

Max Activating Token Index: 487

Text #13

Max Range: 5.7467. Min Range: -5.7467

Max Act: 5.2370. Min Act: -0.0000

Data Index: 501986 (The Pile)

Max Activating Token Index: 673

Text #14

Max Range: 5.7467. Min Range: -5.7467

Max Act: 5.0633. Min Act: -0.0000

Data Index: 1550095 (The Pile)

Max Activating Token Index: 602

Text #15

Max Range: 5.7467. Min Range: -5.7467

Max Act: 4.9303. Min Act: -0.0000

Data Index: 1868891 (The Pile)

Max Activating Token Index: 509

Text #16

Max Range: 5.7467. Min Range: -5.7467

Max Act: 4.4922. Min Act: -0.0000

Data Index: 1789369 (The Pile)

Max Activating Token Index: 919

Text #17

Max Range: 5.7467. Min Range: -5.7467

Max Act: 4.8693. Min Act: -0.0000

Data Index: 1318198 (The Pile)

Max Activating Token Index: 590

Text #18

Max Range: 5.7467. Min Range: -5.7467

Max Act: 3.8264. Min Act: -0.0000

Data Index: 1855212 (The Pile)

Max Activating Token Index: 189

Text #19

Max Range: 5.7467. Min Range: -5.7467

Max Act: 4.1861. Min Act: -0.0000

Data Index: 423533 (The Pile)

Max Activating Token Index: 97