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

Dataset: The Pile

Neuron 1152 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: 1.4214. Min Range: -1.4214

Max Act: 1.4214. Min Act: -0.0000

Data Index: 1930680 (The Pile)

Max Activating Token Index: 952

Text #1

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.3913. Min Act: -0.0000

Data Index: 500882 (The Pile)

Max Activating Token Index: 252

Text #2

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.2872. Min Act: -0.0000

Data Index: 326622 (The Pile)

Max Activating Token Index: 586

Text #3

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.1669. Min Act: -0.0000

Data Index: 1235589 (The Pile)

Max Activating Token Index: 326

Text #4

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.1807. Min Act: -0.0000

Data Index: 560136 (The Pile)

Max Activating Token Index: 298

Text #5

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.0754. Min Act: -0.0000

Data Index: 626332 (The Pile)

Max Activating Token Index: 561

Text #6

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.0198. Min Act: -0.0000

Data Index: 522191 (The Pile)

Max Activating Token Index: 320

Text #7

Max Range: 1.4214. Min Range: -1.4214

Max Act: 0.9864. Min Act: -0.0000

Data Index: 756553 (The Pile)

Max Activating Token Index: 942

Text #8

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.0223. Min Act: -0.0000

Data Index: 742682 (The Pile)

Max Activating Token Index: 531

Text #9

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.0581. Min Act: -0.0000

Data Index: 1425272 (The Pile)

Max Activating Token Index: 610

Text #10

Max Range: 1.4214. Min Range: -1.4214

Max Act: 0.9792. Min Act: -0.0000

Data Index: 82176 (The Pile)

Max Activating Token Index: 116

Text #11

Max Range: 1.4214. Min Range: -1.4214

Max Act: 0.9635. Min Act: -0.0000

Data Index: 780371 (The Pile)

Max Activating Token Index: 373

Text #12

Max Range: 1.4214. Min Range: -1.4214

Max Act: 0.9554. Min Act: -0.0000

Data Index: 1451295 (The Pile)

Max Activating Token Index: 334

Text #13

Max Range: 1.4214. Min Range: -1.4214

Max Act: 1.0140. Min Act: -0.0000

Data Index: 102702 (The Pile)

Max Activating Token Index: 950

Text #14

Max Range: 1.4214. Min Range: -1.4214

Max Act: 0.9205. Min Act: -0.0000

Data Index: 1350992 (The Pile)

Max Activating Token Index: 211

Text #15

Max Range: 1.4214. Min Range: -1.4214

Max Act: 0.9484. Min Act: -0.0000

Data Index: 1322601 (The Pile)

Max Activating Token Index: 639

Text #16

Max Range: 1.4214. Min Range: -1.4214

Max Act: 0.9938. Min Act: -0.0000

Data Index: 632535 (The Pile)

Max Activating Token Index: 90

Text #17

Max Range: 1.4214. Min Range: -1.4214

Max Act: 0.8806. Min Act: -0.0000

Data Index: 1980016 (The Pile)

Max Activating Token Index: 535

Text #18

Max Range: 1.4214. Min Range: -1.4214

Max Act: 0.8989. Min Act: -0.0000

Data Index: 1732178 (The Pile)

Max Activating Token Index: 371

Text #19

Max Range: 1.4214. Min Range: -1.4214

Max Act: 0.9181. Min Act: -0.0000

Data Index: 220282 (The Pile)

Max Activating Token Index: 326