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

Dataset: The Pile

Neuron 3694 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: 0.6557. Min Range: -0.6557

Max Act: 0.6557. Min Act: -0.0000

Data Index: 85867 (The Pile)

Max Activating Token Index: 988

Text #1

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.6405. Min Act: -0.0000

Data Index: 1020770 (The Pile)

Max Activating Token Index: 390

Text #2

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1450347 (The Pile)

Max Activating Token Index: 747

Text #3

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5684. Min Act: -0.0000

Data Index: 201248 (The Pile)

Max Activating Token Index: 400

Text #4

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5630. Min Act: -0.0000

Data Index: 968346 (The Pile)

Max Activating Token Index: 552

Text #5

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5517. Min Act: -0.0000

Data Index: 1082729 (The Pile)

Max Activating Token Index: 401

Text #6

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5156. Min Act: -0.0000

Data Index: 1674626 (The Pile)

Max Activating Token Index: 334

Text #7

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5944. Min Act: -0.0000

Data Index: 461511 (The Pile)

Max Activating Token Index: 299

Text #8

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4232. Min Act: -0.0000

Data Index: 1739446 (The Pile)

Max Activating Token Index: 206

Text #9

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4367. Min Act: -0.0000

Data Index: 1785500 (The Pile)

Max Activating Token Index: 985

Text #10

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.3557. Min Act: -0.0000

Data Index: 867324 (The Pile)

Max Activating Token Index: 937

Text #11

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.3487. Min Act: -0.0000

Data Index: 165475 (The Pile)

Max Activating Token Index: 550

Text #12

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.5056. Min Act: -0.0000

Data Index: 1374560 (The Pile)

Max Activating Token Index: 838

Text #13

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4437. Min Act: -0.0000

Data Index: 97168 (The Pile)

Max Activating Token Index: 1005

Text #14

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4517. Min Act: -0.0000

Data Index: 1758345 (The Pile)

Max Activating Token Index: 844

Text #15

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4166. Min Act: -0.0000

Data Index: 1287605 (The Pile)

Max Activating Token Index: 903

Text #16

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.3438. Min Act: -0.0000

Data Index: 513873 (The Pile)

Max Activating Token Index: 641

Text #17

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4121. Min Act: -0.0000

Data Index: 702366 (The Pile)

Max Activating Token Index: 345

Text #18

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1733903 (The Pile)

Max Activating Token Index: 816

Text #19

Max Range: 0.6557. Min Range: -0.6557

Max Act: 0.3333. Min Act: -0.0000

Data Index: 190041 (The Pile)

Max Activating Token Index: 706