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

Dataset: The Pile

Neuron 1032 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0746. Min Act: -0.0000

Data Index: 1707110 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0717. Min Act: -0.0000

Data Index: 651423 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0591. Min Act: -0.0000

Data Index: 1767009 (The Pile)

Max Activating Token Index: 193

Text #3

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0583. Min Act: -0.0000

Data Index: 1544071 (The Pile)

Max Activating Token Index: 492

Text #4

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0547. Min Act: -0.0000

Data Index: 1471398 (The Pile)

Max Activating Token Index: 511

Text #5

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0547. Min Act: -0.0000

Data Index: 284183 (The Pile)

Max Activating Token Index: 51

Text #6

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0537. Min Act: -0.0000

Data Index: 1651782 (The Pile)

Max Activating Token Index: 594

Text #7

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0537. Min Act: -0.0000

Data Index: 1662161 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0524. Min Act: -0.0000

Data Index: 825364 (The Pile)

Max Activating Token Index: 40

Text #9

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0519. Min Act: -0.0000

Data Index: 152029 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0511. Min Act: -0.0000

Data Index: 1306592 (The Pile)

Max Activating Token Index: 748

Text #11

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0511. Min Act: -0.0000

Data Index: 1111886 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0510. Min Act: -0.0000

Data Index: 963488 (The Pile)

Max Activating Token Index: 869

Text #13

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0506. Min Act: -0.0000

Data Index: 49816 (The Pile)

Max Activating Token Index: 18

Text #14

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0502. Min Act: -0.0000

Data Index: 766224 (The Pile)

Max Activating Token Index: 648

Text #15

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0494. Min Act: -0.0000

Data Index: 392555 (The Pile)

Max Activating Token Index: 465

Text #16

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0505. Min Act: -0.0000

Data Index: 1078273 (The Pile)

Max Activating Token Index: 869

Text #17

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0490. Min Act: -0.0000

Data Index: 1513288 (The Pile)

Max Activating Token Index: 1007

Text #18

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0490. Min Act: -0.0000

Data Index: 1890585 (The Pile)

Max Activating Token Index: 52

Text #19

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0487. Min Act: -0.0000

Data Index: 1367208 (The Pile)

Max Activating Token Index: 618