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

Dataset: The Pile

Neuron 1360 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: 1.9212. Min Range: -1.9212

Max Act: 1.9212. Min Act: -0.0000

Data Index: 1624562 (The Pile)

Max Activating Token Index: 315

Text #1

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.7656. Min Act: -0.0000

Data Index: 1129235 (The Pile)

Max Activating Token Index: 825

Text #2

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.6506. Min Act: -0.0000

Data Index: 986380 (The Pile)

Max Activating Token Index: 776

Text #3

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.5254. Min Act: -0.0000

Data Index: 1881088 (The Pile)

Max Activating Token Index: 66

Text #4

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.7551. Min Act: -0.0000

Data Index: 995408 (The Pile)

Max Activating Token Index: 26

Text #5

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.7040. Min Act: -0.0000

Data Index: 489821 (The Pile)

Max Activating Token Index: 517

Text #6

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.6141. Min Act: -0.0000

Data Index: 952794 (The Pile)

Max Activating Token Index: 517

Text #7

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.4579. Min Act: -0.0000

Data Index: 396748 (The Pile)

Max Activating Token Index: 307

Text #8

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.5261. Min Act: -0.0000

Data Index: 734401 (The Pile)

Max Activating Token Index: 451

Text #9

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.5958. Min Act: -0.0000

Data Index: 1029323 (The Pile)

Max Activating Token Index: 796

Text #10

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.5824. Min Act: -0.0000

Data Index: 600189 (The Pile)

Max Activating Token Index: 648

Text #11

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.4851. Min Act: -0.0000

Data Index: 704214 (The Pile)

Max Activating Token Index: 460

Text #12

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.4852. Min Act: -0.0000

Data Index: 1146157 (The Pile)

Max Activating Token Index: 265

Text #13

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.4628. Min Act: -0.0000

Data Index: 204302 (The Pile)

Max Activating Token Index: 467

Text #14

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.4479. Min Act: -0.0000

Data Index: 470766 (The Pile)

Max Activating Token Index: 241

Text #15

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.4292. Min Act: -0.0000

Data Index: 185510 (The Pile)

Max Activating Token Index: 100

Text #16

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.4260. Min Act: -0.0000

Data Index: 481344 (The Pile)

Max Activating Token Index: 221

Text #17

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.4124. Min Act: -0.0000

Data Index: 1938292 (The Pile)

Max Activating Token Index: 958

Text #18

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.3143. Min Act: -0.0000

Data Index: 227452 (The Pile)

Max Activating Token Index: 957

Text #19

Max Range: 1.9212. Min Range: -1.9212

Max Act: 1.2888. Min Act: -0.0000

Data Index: 718477 (The Pile)

Max Activating Token Index: 863