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

Dataset: The Pile

Neuron 3889 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: 5.6555. Min Range: -5.6555

Max Act: 5.6555. Min Act: -0.0000

Data Index: 1075922 (The Pile)

Max Activating Token Index: 51

Text #1

Max Range: 5.6555. Min Range: -5.6555

Max Act: 5.5294. Min Act: -0.0000

Data Index: 1614317 (The Pile)

Max Activating Token Index: 51

Text #2

Max Range: 5.6555. Min Range: -5.6555

Max Act: 5.5808. Min Act: -0.0000

Data Index: 1804637 (The Pile)

Max Activating Token Index: 32

Text #3

Max Range: 5.6555. Min Range: -5.6555

Max Act: 5.2652. Min Act: -0.0000

Data Index: 1582198 (The Pile)

Max Activating Token Index: 23

Text #4

Max Range: 5.6555. Min Range: -5.6555

Max Act: 5.3313. Min Act: -0.0000

Data Index: 914959 (The Pile)

Max Activating Token Index: 55

Text #5

Max Range: 5.6555. Min Range: -5.6555

Max Act: 5.2764. Min Act: -0.0000

Data Index: 1700858 (The Pile)

Max Activating Token Index: 236

Text #6

Max Range: 5.6555. Min Range: -5.6555

Max Act: 5.0582. Min Act: -0.0000

Data Index: 750377 (The Pile)

Max Activating Token Index: 147

Text #7

Max Range: 5.6555. Min Range: -5.6555

Max Act: 4.9840. Min Act: -0.0000

Data Index: 1631182 (The Pile)

Max Activating Token Index: 230

Text #8

Max Range: 5.6555. Min Range: -5.6555

Max Act: 5.3580. Min Act: -0.0000

Data Index: 1959092 (The Pile)

Max Activating Token Index: 168

Text #9

Max Range: 5.6555. Min Range: -5.6555

Max Act: 5.3794. Min Act: -0.0000

Data Index: 183822 (The Pile)

Max Activating Token Index: 62

Text #10

Max Range: 5.6555. Min Range: -5.6555

Max Act: 4.9710. Min Act: -0.0000

Data Index: 975831 (The Pile)

Max Activating Token Index: 31

Text #11

Max Range: 5.6555. Min Range: -5.6555

Max Act: 5.1479. Min Act: -0.0000

Data Index: 190253 (The Pile)

Max Activating Token Index: 116

Text #12

Max Range: 5.6555. Min Range: -5.6555

Max Act: 4.6517. Min Act: -0.0000

Data Index: 1544769 (The Pile)

Max Activating Token Index: 49

Text #13

Max Range: 5.6555. Min Range: -5.6555

Max Act: 5.0172. Min Act: -0.0000

Data Index: 1227094 (The Pile)

Max Activating Token Index: 23

Text #14

Max Range: 5.6555. Min Range: -5.6555

Max Act: 4.8400. Min Act: -0.0000

Data Index: 1074810 (The Pile)

Max Activating Token Index: 495

Text #15

Max Range: 5.6555. Min Range: -5.6555

Max Act: 5.0116. Min Act: -0.0000

Data Index: 1928652 (The Pile)

Max Activating Token Index: 96

Text #16

Max Range: 5.6555. Min Range: -5.6555

Max Act: 4.7457. Min Act: -0.0000

Data Index: 1588287 (The Pile)

Max Activating Token Index: 88

Text #17

Max Range: 5.6555. Min Range: -5.6555

Max Act: 4.5985. Min Act: -0.0000

Data Index: 801679 (The Pile)

Max Activating Token Index: 251

Text #18

Max Range: 5.6555. Min Range: -5.6555

Max Act: 4.5944. Min Act: -0.0000

Data Index: 981826 (The Pile)

Max Activating Token Index: 400

Text #19

Max Range: 5.6555. Min Range: -5.6555

Max Act: 5.1134. Min Act: -0.0000

Data Index: 370258 (The Pile)

Max Activating Token Index: 149