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

Dataset: The Pile

Neuron 4660 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: 0.7926. Min Range: -0.7926

Max Act: 0.7926. Min Act: -0.0000

Data Index: 1100058 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.7656. Min Act: -0.0000

Data Index: 1444648 (The Pile)

Max Activating Token Index: 24

Text #2

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6052. Min Act: -0.0000

Data Index: 648051 (The Pile)

Max Activating Token Index: 27

Text #3

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5928. Min Act: -0.0000

Data Index: 1703749 (The Pile)

Max Activating Token Index: 81

Text #4

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1660889 (The Pile)

Max Activating Token Index: 16

Text #5

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6420. Min Act: -0.0000

Data Index: 965884 (The Pile)

Max Activating Token Index: 439

Text #6

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.6428. Min Act: -0.0000

Data Index: 1831064 (The Pile)

Max Activating Token Index: 95

Text #7

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5885. Min Act: -0.0000

Data Index: 530880 (The Pile)

Max Activating Token Index: 352

Text #8

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5647. Min Act: -0.0000

Data Index: 367780 (The Pile)

Max Activating Token Index: 94

Text #9

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5508. Min Act: -0.0000

Data Index: 680940 (The Pile)

Max Activating Token Index: 127

Text #10

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5646. Min Act: -0.0000

Data Index: 1486902 (The Pile)

Max Activating Token Index: 889

Text #11

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1459563 (The Pile)

Max Activating Token Index: 254

Text #12

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1531572 (The Pile)

Max Activating Token Index: 406

Text #13

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5185. Min Act: -0.0000

Data Index: 1599679 (The Pile)

Max Activating Token Index: 49

Text #14

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5494. Min Act: -0.0000

Data Index: 1090000 (The Pile)

Max Activating Token Index: 27

Text #15

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5653. Min Act: -0.0000

Data Index: 48075 (The Pile)

Max Activating Token Index: 55

Text #16

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5645. Min Act: -0.0000

Data Index: 1913963 (The Pile)

Max Activating Token Index: 33

Text #17

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5372. Min Act: -0.0000

Data Index: 784161 (The Pile)

Max Activating Token Index: 35

Text #18

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5198. Min Act: -0.0000

Data Index: 1750166 (The Pile)

Max Activating Token Index: 14

Text #19

Max Range: 0.7926. Min Range: -0.7926

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1408189 (The Pile)

Max Activating Token Index: 109