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

Dataset: The Pile

Neuron 4447 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: 1.3197. Min Range: -1.3197

Max Act: 1.3197. Min Act: -0.0000

Data Index: 1434969 (The Pile)

Max Activating Token Index: 483

Text #1

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.2815. Min Act: -0.0000

Data Index: 1534046 (The Pile)

Max Activating Token Index: 21

Text #2

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.2530. Min Act: -0.0000

Data Index: 135573 (The Pile)

Max Activating Token Index: 79

Text #3

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.2271. Min Act: -0.0000

Data Index: 843291 (The Pile)

Max Activating Token Index: 61

Text #4

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.2425. Min Act: -0.0000

Data Index: 1126756 (The Pile)

Max Activating Token Index: 292

Text #5

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.2320. Min Act: -0.0000

Data Index: 1590224 (The Pile)

Max Activating Token Index: 334

Text #6

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.2093. Min Act: -0.0000

Data Index: 40552 (The Pile)

Max Activating Token Index: 460

Text #7

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.0781. Min Act: -0.0000

Data Index: 1409784 (The Pile)

Max Activating Token Index: 572

Text #8

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.1674. Min Act: -0.0000

Data Index: 1788005 (The Pile)

Max Activating Token Index: 106

Text #9

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.0984. Min Act: -0.0000

Data Index: 513078 (The Pile)

Max Activating Token Index: 254

Text #10

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.0706. Min Act: -0.0000

Data Index: 1646903 (The Pile)

Max Activating Token Index: 1002

Text #11

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.1693. Min Act: -0.0000

Data Index: 1310797 (The Pile)

Max Activating Token Index: 597

Text #12

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.1528. Min Act: -0.0000

Data Index: 191276 (The Pile)

Max Activating Token Index: 8

Text #13

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.0855. Min Act: -0.0000

Data Index: 1580114 (The Pile)

Max Activating Token Index: 125

Text #14

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.1357. Min Act: -0.0000

Data Index: 1096648 (The Pile)

Max Activating Token Index: 27

Text #15

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.1920. Min Act: -0.0000

Data Index: 1231105 (The Pile)

Max Activating Token Index: 62

Text #16

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.1827. Min Act: -0.0000

Data Index: 875871 (The Pile)

Max Activating Token Index: 152

Text #17

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.1010. Min Act: -0.0000

Data Index: 16483 (The Pile)

Max Activating Token Index: 635

Text #18

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.0900. Min Act: -0.0000

Data Index: 1195889 (The Pile)

Max Activating Token Index: 55

Text #19

Max Range: 1.3197. Min Range: -1.3197

Max Act: 1.0294. Min Act: -0.0000

Data Index: 1030616 (The Pile)

Max Activating Token Index: 964