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

Dataset: The Pile

Neuron 3239 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 5.8776. Min Range: -5.8776

Max Act: 5.8776. Min Act: -0.0000

Data Index: 1367715 (The Pile)

Max Activating Token Index: 779

Text #1

Max Range: 5.8776. Min Range: -5.8776

Max Act: 5.3468. Min Act: -0.0000

Data Index: 1010262 (The Pile)

Max Activating Token Index: 944

Text #2

Max Range: 5.8776. Min Range: -5.8776

Max Act: 4.6757. Min Act: -0.0000

Data Index: 403417 (The Pile)

Max Activating Token Index: 912

Text #3

Max Range: 5.8776. Min Range: -5.8776

Max Act: 4.1093. Min Act: -0.0000

Data Index: 1867785 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 5.8776. Min Range: -5.8776

Max Act: 3.9199. Min Act: -0.0000

Data Index: 287135 (The Pile)

Max Activating Token Index: 911

Text #5

Max Range: 5.8776. Min Range: -5.8776

Max Act: 3.9964. Min Act: -0.0000

Data Index: 1483304 (The Pile)

Max Activating Token Index: 739

Text #6

Max Range: 5.8776. Min Range: -5.8776

Max Act: 3.9609. Min Act: -0.0000

Data Index: 181155 (The Pile)

Max Activating Token Index: 132

Text #7

Max Range: 5.8776. Min Range: -5.8776

Max Act: 3.8734. Min Act: -0.0000

Data Index: 1969805 (The Pile)

Max Activating Token Index: 106

Text #8

Max Range: 5.8776. Min Range: -5.8776

Max Act: 2.2826. Min Act: -0.0000

Data Index: 1904536 (The Pile)

Max Activating Token Index: 860

Text #9

Max Range: 5.8776. Min Range: -5.8776

Max Act: 3.6517. Min Act: -0.0000

Data Index: 1807295 (The Pile)

Max Activating Token Index: 265

Text #10

Max Range: 5.8776. Min Range: -5.8776

Max Act: 3.4192. Min Act: -0.0000

Data Index: 936477 (The Pile)

Max Activating Token Index: 179

Text #11

Max Range: 5.8776. Min Range: -5.8776

Max Act: 3.2320. Min Act: -0.0000

Data Index: 212517 (The Pile)

Max Activating Token Index: 499

Text #12

Max Range: 5.8776. Min Range: -5.8776

Max Act: 3.1598. Min Act: -0.0000

Data Index: 250315 (The Pile)

Max Activating Token Index: 925

Text #13

Max Range: 5.8776. Min Range: -5.8776

Max Act: 3.4332. Min Act: -0.0000

Data Index: 1535637 (The Pile)

Max Activating Token Index: 390

Text #14

Max Range: 5.8776. Min Range: -5.8776

Max Act: 2.8409. Min Act: -0.0000

Data Index: 737727 (The Pile)

Max Activating Token Index: 822

Text #15

Max Range: 5.8776. Min Range: -5.8776

Max Act: 3.4911. Min Act: -0.0000

Data Index: 365373 (The Pile)

Max Activating Token Index: 821

Text #16

Max Range: 5.8776. Min Range: -5.8776

Max Act: 2.8098. Min Act: -0.0000

Data Index: 1229580 (The Pile)

Max Activating Token Index: 640

Text #17

Max Range: 5.8776. Min Range: -5.8776

Max Act: 3.6842. Min Act: -0.0000

Data Index: 1419133 (The Pile)

Max Activating Token Index: 1011

Text #18

Max Range: 5.8776. Min Range: -5.8776

Max Act: 3.3527. Min Act: -0.0000

Data Index: 1607788 (The Pile)

Max Activating Token Index: 3

Text #19

Max Range: 5.8776. Min Range: -5.8776

Max Act: 3.3454. Min Act: -0.0000

Data Index: 218795 (The Pile)

Max Activating Token Index: 414