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

Dataset: The Pile

Neuron 1140 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0712. Min Range: -1.0712

Max Act: 1.0712. Min Act: -0.0000

Data Index: 749559 (The Pile)

Max Activating Token Index: 421

Text #1

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.7905. Min Act: -0.0000

Data Index: 1371402 (The Pile)

Max Activating Token Index: 717

Text #2

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.7806. Min Act: -0.0000

Data Index: 323594 (The Pile)

Max Activating Token Index: 703

Text #3

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.8407. Min Act: -0.0000

Data Index: 823834 (The Pile)

Max Activating Token Index: 855

Text #4

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.7849. Min Act: -0.0000

Data Index: 1601763 (The Pile)

Max Activating Token Index: 861

Text #5

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.7710. Min Act: 0.0000

Data Index: 1674183 (The Pile)

Max Activating Token Index: 159

Text #6

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.7482. Min Act: -0.0000

Data Index: 1339417 (The Pile)

Max Activating Token Index: 963

Text #7

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.6769. Min Act: -0.0000

Data Index: 985210 (The Pile)

Max Activating Token Index: 573

Text #8

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.7153. Min Act: -0.0000

Data Index: 387958 (The Pile)

Max Activating Token Index: 920

Text #9

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.6953. Min Act: -0.0000

Data Index: 1699554 (The Pile)

Max Activating Token Index: 1006

Text #10

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.6104. Min Act: -0.0000

Data Index: 137950 (The Pile)

Max Activating Token Index: 579

Text #11

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.5937. Min Act: -0.0000

Data Index: 697542 (The Pile)

Max Activating Token Index: 268

Text #12

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.6260. Min Act: -0.0000

Data Index: 878298 (The Pile)

Max Activating Token Index: 664

Text #13

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.5387. Min Act: -0.0000

Data Index: 749336 (The Pile)

Max Activating Token Index: 951

Text #14

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.5663. Min Act: -0.0000

Data Index: 667454 (The Pile)

Max Activating Token Index: 916

Text #15

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.5641. Min Act: -0.0000

Data Index: 889122 (The Pile)

Max Activating Token Index: 629

Text #16

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.5386. Min Act: -0.0000

Data Index: 619635 (The Pile)

Max Activating Token Index: 213

Text #17

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.5350. Min Act: 0.0000

Data Index: 730532 (The Pile)

Max Activating Token Index: 276

Text #18

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.4948. Min Act: -0.0000

Data Index: 1442373 (The Pile)

Max Activating Token Index: 173

Text #19

Max Range: 1.0712. Min Range: -1.0712

Max Act: 0.4814. Min Act: 0.0001

Data Index: 1407482 (The Pile)

Max Activating Token Index: 432