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

Dataset: The Pile

Neuron 2032 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: 1.2789. Min Range: -1.2789

Max Act: 1.2433. Min Act: -0.0000

Data Index: 664966 (The Pile)

Max Activating Token Index: 978

Text #1

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.2789. Min Act: -0.0000

Data Index: 493133 (The Pile)

Max Activating Token Index: 934

Text #2

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.1650. Min Act: -0.0000

Data Index: 1004823 (The Pile)

Max Activating Token Index: 89

Text #3

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.1903. Min Act: -0.0000

Data Index: 835440 (The Pile)

Max Activating Token Index: 682

Text #4

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0463. Min Act: -0.0000

Data Index: 1216731 (The Pile)

Max Activating Token Index: 65

Text #5

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0141. Min Act: -0.0000

Data Index: 1248424 (The Pile)

Max Activating Token Index: 90

Text #6

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0078. Min Act: -0.0000

Data Index: 1236884 (The Pile)

Max Activating Token Index: 769

Text #7

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0248. Min Act: -0.0000

Data Index: 852362 (The Pile)

Max Activating Token Index: 37

Text #8

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0184. Min Act: -0.0000

Data Index: 424700 (The Pile)

Max Activating Token Index: 47

Text #9

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0479. Min Act: -0.0000

Data Index: 1605664 (The Pile)

Max Activating Token Index: 31

Text #10

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0125. Min Act: -0.0000

Data Index: 1690624 (The Pile)

Max Activating Token Index: 72

Text #11

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0145. Min Act: -0.0000

Data Index: 826389 (The Pile)

Max Activating Token Index: 62

Text #12

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.9104. Min Act: -0.0000

Data Index: 1977852 (The Pile)

Max Activating Token Index: 35

Text #13

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.9346. Min Act: -0.0000

Data Index: 1883815 (The Pile)

Max Activating Token Index: 235

Text #14

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0198. Min Act: -0.0000

Data Index: 913171 (The Pile)

Max Activating Token Index: 822

Text #15

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.9566. Min Act: -0.0000

Data Index: 1834845 (The Pile)

Max Activating Token Index: 115

Text #16

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.9809. Min Act: -0.0000

Data Index: 672161 (The Pile)

Max Activating Token Index: 139

Text #17

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.9525. Min Act: -0.0000

Data Index: 411034 (The Pile)

Max Activating Token Index: 897

Text #18

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.9121. Min Act: -0.0000

Data Index: 21355 (The Pile)

Max Activating Token Index: 386

Text #19

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.9598. Min Act: -0.0000

Data Index: 581382 (The Pile)

Max Activating Token Index: 209