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

Dataset: The Pile

Neuron 1623 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8851. Min Range: -1.8851

Max Act: 1.8851. Min Act: -0.0000

Data Index: 1517048 (The Pile)

Max Activating Token Index: 549

Text #1

Max Range: 1.8851. Min Range: -1.8851

Max Act: 1.7303. Min Act: -0.0000

Data Index: 1433793 (The Pile)

Max Activating Token Index: 358

Text #2

Max Range: 1.8851. Min Range: -1.8851

Max Act: 1.8711. Min Act: -0.0000

Data Index: 1814337 (The Pile)

Max Activating Token Index: 406

Text #3

Max Range: 1.8851. Min Range: -1.8851

Max Act: 1.4364. Min Act: -0.0000

Data Index: 1618414 (The Pile)

Max Activating Token Index: 902

Text #4

Max Range: 1.8851. Min Range: -1.8851

Max Act: 1.7520. Min Act: -0.0000

Data Index: 1938094 (The Pile)

Max Activating Token Index: 378

Text #5

Max Range: 1.8851. Min Range: -1.8851

Max Act: 1.6418. Min Act: -0.0000

Data Index: 322713 (The Pile)

Max Activating Token Index: 315

Text #6

Max Range: 1.8851. Min Range: -1.8851

Max Act: 1.6955. Min Act: -0.0000

Data Index: 1486869 (The Pile)

Max Activating Token Index: 420

Text #7

Max Range: 1.8851. Min Range: -1.8851

Max Act: 1.5585. Min Act: -0.0000

Data Index: 1350545 (The Pile)

Max Activating Token Index: 404

Text #8

Max Range: 1.8851. Min Range: -1.8851

Max Act: 1.6268. Min Act: -0.0000

Data Index: 134866 (The Pile)

Max Activating Token Index: 442

Text #9

Max Range: 1.8851. Min Range: -1.8851

Max Act: 1.5291. Min Act: -0.0000

Data Index: 1268413 (The Pile)

Max Activating Token Index: 336

Text #10

Max Range: 1.8851. Min Range: -1.8851

Max Act: 1.4312. Min Act: -0.0000

Data Index: 1589038 (The Pile)

Max Activating Token Index: 296

Text #11

Max Range: 1.8851. Min Range: -1.8851

Max Act: 1.6098. Min Act: -0.0000

Data Index: 1097187 (The Pile)

Max Activating Token Index: 270

Text #12

Max Range: 1.8851. Min Range: -1.8851

Max Act: 1.4897. Min Act: -0.0000

Data Index: 703049 (The Pile)

Max Activating Token Index: 761

Text #13

Max Range: 1.8851. Min Range: -1.8851

Max Act: 1.6600. Min Act: 0.0001

Data Index: 1003663 (The Pile)

Max Activating Token Index: 814

Text #14

Max Range: 1.8851. Min Range: -1.8851

Max Act: 1.4786. Min Act: -0.0000

Data Index: 1071983 (The Pile)

Max Activating Token Index: 777

Text #15

Max Range: 1.8851. Min Range: -1.8851

Max Act: 1.6613. Min Act: -0.0000

Data Index: 1630497 (The Pile)

Max Activating Token Index: 180

Text #16

Max Range: 1.8851. Min Range: -1.8851

Max Act: 1.4707. Min Act: -0.0000

Data Index: 1188563 (The Pile)

Max Activating Token Index: 488

Text #17

Max Range: 1.8851. Min Range: -1.8851

Max Act: 1.5413. Min Act: -0.0000

Data Index: 631312 (The Pile)

Max Activating Token Index: 506

Text #18

Max Range: 1.8851. Min Range: -1.8851

Max Act: 1.4483. Min Act: -0.0000

Data Index: 957014 (The Pile)

Max Activating Token Index: 631

Text #19

Max Range: 1.8851. Min Range: -1.8851

Max Act: 1.4323. Min Act: -0.0000

Data Index: 1706339 (The Pile)

Max Activating Token Index: 627