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

Dataset: The Pile

Neuron 387 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: 1.1723. Min Range: -1.1723

Max Act: 1.1723. Min Act: -0.0000

Data Index: 564433 (The Pile)

Max Activating Token Index: 718

Text #1

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.9830. Min Act: -0.0000

Data Index: 982703 (The Pile)

Max Activating Token Index: 811

Text #2

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.8839. Min Act: -0.0000

Data Index: 97484 (The Pile)

Max Activating Token Index: 854

Text #3

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.8566. Min Act: -0.0000

Data Index: 218393 (The Pile)

Max Activating Token Index: 482

Text #4

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.8130. Min Act: -0.0000

Data Index: 1037599 (The Pile)

Max Activating Token Index: 637

Text #5

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.8496. Min Act: -0.0000

Data Index: 1936538 (The Pile)

Max Activating Token Index: 766

Text #6

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.7697. Min Act: -0.0000

Data Index: 473457 (The Pile)

Max Activating Token Index: 939

Text #7

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.7672. Min Act: -0.0000

Data Index: 1072149 (The Pile)

Max Activating Token Index: 892

Text #8

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.8559. Min Act: -0.0000

Data Index: 313981 (The Pile)

Max Activating Token Index: 871

Text #9

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.8417. Min Act: -0.0000

Data Index: 958302 (The Pile)

Max Activating Token Index: 951

Text #10

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.7202. Min Act: -0.0000

Data Index: 61486 (The Pile)

Max Activating Token Index: 854

Text #11

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.7677. Min Act: -0.0000

Data Index: 886651 (The Pile)

Max Activating Token Index: 179

Text #12

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.7354. Min Act: -0.0000

Data Index: 1240719 (The Pile)

Max Activating Token Index: 333

Text #13

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.7556. Min Act: -0.0000

Data Index: 821967 (The Pile)

Max Activating Token Index: 845

Text #14

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.7183. Min Act: -0.0000

Data Index: 708675 (The Pile)

Max Activating Token Index: 62

Text #15

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.7148. Min Act: -0.0000

Data Index: 1789028 (The Pile)

Max Activating Token Index: 755

Text #16

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.7746. Min Act: -0.0000

Data Index: 437951 (The Pile)

Max Activating Token Index: 568

Text #17

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.6948. Min Act: -0.0000

Data Index: 436231 (The Pile)

Max Activating Token Index: 722

Text #18

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.5467. Min Act: -0.0000

Data Index: 1568864 (The Pile)

Max Activating Token Index: 792

Text #19

Max Range: 1.1723. Min Range: -1.1723

Max Act: 0.6560. Min Act: -0.0000

Data Index: 1600155 (The Pile)

Max Activating Token Index: 156