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

Dataset: The Pile

Neuron 4420 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.7450. Min Act: -0.0000

Data Index: 1775177 (The Pile)

Max Activating Token Index: 792

Text #1

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.7103. Min Act: -0.0000

Data Index: 815832 (The Pile)

Max Activating Token Index: 78

Text #2

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.4022. Min Act: -0.0000

Data Index: 1080219 (The Pile)

Max Activating Token Index: 120

Text #3

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.1532. Min Act: -0.0000

Data Index: 1703309 (The Pile)

Max Activating Token Index: 734

Text #4

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.2840. Min Act: -0.0000

Data Index: 1990838 (The Pile)

Max Activating Token Index: 106

Text #5

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.2297. Min Act: -0.0000

Data Index: 1786520 (The Pile)

Max Activating Token Index: 141

Text #6

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.2930. Min Act: -0.0000

Data Index: 86779 (The Pile)

Max Activating Token Index: 26

Text #7

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.1651. Min Act: -0.0000

Data Index: 1464416 (The Pile)

Max Activating Token Index: 41

Text #8

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.1375. Min Act: -0.0000

Data Index: 1005647 (The Pile)

Max Activating Token Index: 885

Text #9

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.1402. Min Act: -0.0000

Data Index: 85268 (The Pile)

Max Activating Token Index: 502

Text #10

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.0887. Min Act: -0.0000

Data Index: 675173 (The Pile)

Max Activating Token Index: 83

Text #11

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.1683. Min Act: -0.0000

Data Index: 823181 (The Pile)

Max Activating Token Index: 11

Text #12

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.1854. Min Act: -0.0000

Data Index: 36525 (The Pile)

Max Activating Token Index: 81

Text #13

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.1696. Min Act: -0.0000

Data Index: 1839135 (The Pile)

Max Activating Token Index: 432

Text #14

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.1337. Min Act: -0.0000

Data Index: 333746 (The Pile)

Max Activating Token Index: 47

Text #15

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.1268. Min Act: -0.0000

Data Index: 62008 (The Pile)

Max Activating Token Index: 554

Text #16

Max Range: 1.7450. Min Range: -1.7450

Max Act: 0.9945. Min Act: -0.0000

Data Index: 1136106 (The Pile)

Max Activating Token Index: 981

Text #17

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.0549. Min Act: -0.0000

Data Index: 1676530 (The Pile)

Max Activating Token Index: 799

Text #18

Max Range: 1.7450. Min Range: -1.7450

Max Act: 1.1103. Min Act: -0.0000

Data Index: 649090 (The Pile)

Max Activating Token Index: 223

Text #19

Max Range: 1.7450. Min Range: -1.7450

Max Act: 0.9800. Min Act: -0.0000

Data Index: 292039 (The Pile)

Max Activating Token Index: 808