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

Dataset: The Pile

Neuron 3565 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.3139. Min Act: -0.0000

Data Index: 1901341 (The Pile)

Max Activating Token Index: 844

Text #1

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2381. Min Act: -0.0000

Data Index: 370560 (The Pile)

Max Activating Token Index: 894

Text #2

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2378. Min Act: -0.0000

Data Index: 1728397 (The Pile)

Max Activating Token Index: 978

Text #3

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1856919 (The Pile)

Max Activating Token Index: 757

Text #4

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2314. Min Act: -0.0000

Data Index: 1120860 (The Pile)

Max Activating Token Index: 1014

Text #5

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2214. Min Act: -0.0000

Data Index: 259347 (The Pile)

Max Activating Token Index: 976

Text #6

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1473856 (The Pile)

Max Activating Token Index: 175

Text #7

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2173. Min Act: -0.0000

Data Index: 669636 (The Pile)

Max Activating Token Index: 802

Text #8

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2277. Min Act: -0.0000

Data Index: 1528764 (The Pile)

Max Activating Token Index: 880

Text #9

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.1970. Min Act: -0.0000

Data Index: 837105 (The Pile)

Max Activating Token Index: 393

Text #10

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1787140 (The Pile)

Max Activating Token Index: 552

Text #11

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.2288. Min Act: -0.0000

Data Index: 1113698 (The Pile)

Max Activating Token Index: 882

Text #12

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.1982. Min Act: -0.0000

Data Index: 1134673 (The Pile)

Max Activating Token Index: 884

Text #13

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.1940. Min Act: -0.0000

Data Index: 1304040 (The Pile)

Max Activating Token Index: 146

Text #14

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.1710. Min Act: -0.0000

Data Index: 1930640 (The Pile)

Max Activating Token Index: 532

Text #15

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.1669. Min Act: -0.0000

Data Index: 16785 (The Pile)

Max Activating Token Index: 878

Text #16

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.1793. Min Act: -0.0000

Data Index: 1996774 (The Pile)

Max Activating Token Index: 160

Text #17

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.1598. Min Act: -0.0000

Data Index: 977168 (The Pile)

Max Activating Token Index: 946

Text #18

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.1732. Min Act: -0.0000

Data Index: 367035 (The Pile)

Max Activating Token Index: 750

Text #19

Max Range: 0.3139. Min Range: -0.3139

Max Act: 0.1633. Min Act: -0.0000

Data Index: 1743542 (The Pile)

Max Activating Token Index: 880