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

Dataset: The Pile

Neuron 2569 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: 4.6057. Min Range: -4.6057

Max Act: 4.6057. Min Act: -0.0000

Data Index: 1015985 (The Pile)

Max Activating Token Index: 501

Text #1

Max Range: 4.6057. Min Range: -4.6057

Max Act: 4.4178. Min Act: -0.0000

Data Index: 1446715 (The Pile)

Max Activating Token Index: 393

Text #2

Max Range: 4.6057. Min Range: -4.6057

Max Act: 4.5440. Min Act: -0.0000

Data Index: 100399 (The Pile)

Max Activating Token Index: 564

Text #3

Max Range: 4.6057. Min Range: -4.6057

Max Act: 4.3776. Min Act: -0.0000

Data Index: 1331436 (The Pile)

Max Activating Token Index: 469

Text #4

Max Range: 4.6057. Min Range: -4.6057

Max Act: 4.1568. Min Act: -0.0000

Data Index: 1374002 (The Pile)

Max Activating Token Index: 66

Text #5

Max Range: 4.6057. Min Range: -4.6057

Max Act: 4.2230. Min Act: -0.0000

Data Index: 580099 (The Pile)

Max Activating Token Index: 994

Text #6

Max Range: 4.6057. Min Range: -4.6057

Max Act: 3.8905. Min Act: -0.0000

Data Index: 258219 (The Pile)

Max Activating Token Index: 89

Text #7

Max Range: 4.6057. Min Range: -4.6057

Max Act: 3.8670. Min Act: -0.0000

Data Index: 1256096 (The Pile)

Max Activating Token Index: 80

Text #8

Max Range: 4.6057. Min Range: -4.6057

Max Act: 3.7699. Min Act: -0.0000

Data Index: 654713 (The Pile)

Max Activating Token Index: 120

Text #9

Max Range: 4.6057. Min Range: -4.6057

Max Act: 3.1627. Min Act: -0.0000

Data Index: 1789717 (The Pile)

Max Activating Token Index: 925

Text #10

Max Range: 4.6057. Min Range: -4.6057

Max Act: 3.4328. Min Act: -0.0000

Data Index: 1610158 (The Pile)

Max Activating Token Index: 22

Text #11

Max Range: 4.6057. Min Range: -4.6057

Max Act: 3.5837. Min Act: -0.0000

Data Index: 1691038 (The Pile)

Max Activating Token Index: 45

Text #12

Max Range: 4.6057. Min Range: -4.6057

Max Act: 3.5518. Min Act: -0.0000

Data Index: 661396 (The Pile)

Max Activating Token Index: 90

Text #13

Max Range: 4.6057. Min Range: -4.6057

Max Act: 3.5625. Min Act: -0.0000

Data Index: 259203 (The Pile)

Max Activating Token Index: 56

Text #14

Max Range: 4.6057. Min Range: -4.6057

Max Act: 3.3697. Min Act: -0.0000

Data Index: 566267 (The Pile)

Max Activating Token Index: 715

Text #15

Max Range: 4.6057. Min Range: -4.6057

Max Act: 3.4594. Min Act: -0.0000

Data Index: 1930523 (The Pile)

Max Activating Token Index: 222

Text #16

Max Range: 4.6057. Min Range: -4.6057

Max Act: 3.2788. Min Act: -0.0000

Data Index: 855176 (The Pile)

Max Activating Token Index: 85

Text #17

Max Range: 4.6057. Min Range: -4.6057

Max Act: 3.2758. Min Act: -0.0000

Data Index: 837490 (The Pile)

Max Activating Token Index: 31

Text #18

Max Range: 4.6057. Min Range: -4.6057

Max Act: 3.2417. Min Act: -0.0000

Data Index: 1840013 (The Pile)

Max Activating Token Index: 121

Text #19

Max Range: 4.6057. Min Range: -4.6057

Max Act: 3.2311. Min Act: -0.0000

Data Index: 1459733 (The Pile)

Max Activating Token Index: 8