Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1012 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2375. Min Range: -1.2375

Max Act: 1.2375. Min Act: -0.0000

Data Index: 1081252 (The Pile)

Max Activating Token Index: 926

Text #1

Max Range: 1.2375. Min Range: -1.2375

Max Act: 1.2136. Min Act: -0.0000

Data Index: 626754 (The Pile)

Max Activating Token Index: 534

Text #2

Max Range: 1.2375. Min Range: -1.2375

Max Act: 1.2010. Min Act: 0.0000

Data Index: 1067174 (The Pile)

Max Activating Token Index: 715

Text #3

Max Range: 1.2375. Min Range: -1.2375

Max Act: 1.1423. Min Act: -0.0000

Data Index: 1456408 (The Pile)

Max Activating Token Index: 895

Text #4

Max Range: 1.2375. Min Range: -1.2375

Max Act: 1.1379. Min Act: -0.0000

Data Index: 1073012 (The Pile)

Max Activating Token Index: 547

Text #5

Max Range: 1.2375. Min Range: -1.2375

Max Act: 1.1878. Min Act: -0.0000

Data Index: 1888449 (The Pile)

Max Activating Token Index: 457

Text #6

Max Range: 1.2375. Min Range: -1.2375

Max Act: 1.1852. Min Act: -0.0000

Data Index: 1241761 (The Pile)

Max Activating Token Index: 613

Text #7

Max Range: 1.2375. Min Range: -1.2375

Max Act: 1.1756. Min Act: -0.0000

Data Index: 1308799 (The Pile)

Max Activating Token Index: 139

Text #8

Max Range: 1.2375. Min Range: -1.2375

Max Act: 1.1767. Min Act: -0.0000

Data Index: 538217 (The Pile)

Max Activating Token Index: 356

Text #9

Max Range: 1.2375. Min Range: -1.2375

Max Act: 1.1028. Min Act: -0.0000

Data Index: 1833015 (The Pile)

Max Activating Token Index: 597

Text #10

Max Range: 1.2375. Min Range: -1.2375

Max Act: 1.0557. Min Act: -0.0000

Data Index: 1622760 (The Pile)

Max Activating Token Index: 200

Text #11

Max Range: 1.2375. Min Range: -1.2375

Max Act: 1.0655. Min Act: 0.0000

Data Index: 173130 (The Pile)

Max Activating Token Index: 550

Text #12

Max Range: 1.2375. Min Range: -1.2375

Max Act: 1.0506. Min Act: -0.0000

Data Index: 259735 (The Pile)

Max Activating Token Index: 372

Text #13

Max Range: 1.2375. Min Range: -1.2375

Max Act: 1.0396. Min Act: -0.0000

Data Index: 1644678 (The Pile)

Max Activating Token Index: 311

Text #14

Max Range: 1.2375. Min Range: -1.2375

Max Act: 1.0509. Min Act: 0.0000

Data Index: 1605824 (The Pile)

Max Activating Token Index: 660

Text #15

Max Range: 1.2375. Min Range: -1.2375

Max Act: 1.0238. Min Act: -0.0000

Data Index: 1882512 (The Pile)

Max Activating Token Index: 413

Text #16

Max Range: 1.2375. Min Range: -1.2375

Max Act: 1.0176. Min Act: -0.0000

Data Index: 1421014 (The Pile)

Max Activating Token Index: 273

Text #17

Max Range: 1.2375. Min Range: -1.2375

Max Act: 1.0129. Min Act: -0.0000

Data Index: 969292 (The Pile)

Max Activating Token Index: 120

Text #18

Max Range: 1.2375. Min Range: -1.2375

Max Act: 0.9203. Min Act: -0.0000

Data Index: 1635685 (The Pile)

Max Activating Token Index: 618

Text #19

Max Range: 1.2375. Min Range: -1.2375

Max Act: 1.0344. Min Act: -0.0000

Data Index: 1156521 (The Pile)

Max Activating Token Index: 380