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

Dataset: The Pile

Neuron 2782 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2201. Min Range: -1.2201

Max Act: 1.0514. Min Act: -0.0000

Data Index: 310761 (The Pile)

Max Activating Token Index: 39

Text #1

Max Range: 1.2201. Min Range: -1.2201

Max Act: 1.2201. Min Act: -0.0000

Data Index: 59450 (The Pile)

Max Activating Token Index: 882

Text #2

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.9387. Min Act: -0.0000

Data Index: 760842 (The Pile)

Max Activating Token Index: 891

Text #3

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.9123. Min Act: -0.0000

Data Index: 513855 (The Pile)

Max Activating Token Index: 491

Text #4

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.9050. Min Act: -0.0000

Data Index: 1383446 (The Pile)

Max Activating Token Index: 241

Text #5

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.8374. Min Act: -0.0000

Data Index: 1331766 (The Pile)

Max Activating Token Index: 523

Text #6

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.7543. Min Act: -0.0000

Data Index: 155536 (The Pile)

Max Activating Token Index: 399

Text #7

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1710252 (The Pile)

Max Activating Token Index: 349

Text #8

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.7426. Min Act: -0.0000

Data Index: 1187751 (The Pile)

Max Activating Token Index: 436

Text #9

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.6488. Min Act: -0.0000

Data Index: 1195438 (The Pile)

Max Activating Token Index: 971

Text #10

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.7812. Min Act: -0.0000

Data Index: 63574 (The Pile)

Max Activating Token Index: 478

Text #11

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.7805. Min Act: -0.0000

Data Index: 87350 (The Pile)

Max Activating Token Index: 496

Text #12

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.6835. Min Act: -0.0000

Data Index: 1176161 (The Pile)

Max Activating Token Index: 741

Text #13

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.7046. Min Act: -0.0000

Data Index: 472995 (The Pile)

Max Activating Token Index: 36

Text #14

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.7541. Min Act: -0.0000

Data Index: 849467 (The Pile)

Max Activating Token Index: 838

Text #15

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.6595. Min Act: -0.0000

Data Index: 1799993 (The Pile)

Max Activating Token Index: 984

Text #16

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.6536. Min Act: -0.0000

Data Index: 1201881 (The Pile)

Max Activating Token Index: 202

Text #17

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.7210. Min Act: -0.0000

Data Index: 1571356 (The Pile)

Max Activating Token Index: 282

Text #18

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.5869. Min Act: -0.0000

Data Index: 396244 (The Pile)

Max Activating Token Index: 586

Text #19

Max Range: 1.2201. Min Range: -1.2201

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1338461 (The Pile)

Max Activating Token Index: 568