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

Dataset: The Pile

Neuron 3853 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0683. Min Range: -2.0683

Max Act: 2.0683. Min Act: -0.0000

Data Index: 521034 (The Pile)

Max Activating Token Index: 846

Text #1

Max Range: 2.0683. Min Range: -2.0683

Max Act: 1.9434. Min Act: -0.0000

Data Index: 813208 (The Pile)

Max Activating Token Index: 764

Text #2

Max Range: 2.0683. Min Range: -2.0683

Max Act: 1.9002. Min Act: -0.0000

Data Index: 1846943 (The Pile)

Max Activating Token Index: 679

Text #3

Max Range: 2.0683. Min Range: -2.0683

Max Act: 1.8742. Min Act: -0.0000

Data Index: 1628323 (The Pile)

Max Activating Token Index: 326

Text #4

Max Range: 2.0683. Min Range: -2.0683

Max Act: 1.7299. Min Act: -0.0000

Data Index: 1012056 (The Pile)

Max Activating Token Index: 86

Text #5

Max Range: 2.0683. Min Range: -2.0683

Max Act: 1.7241. Min Act: -0.0000

Data Index: 1441125 (The Pile)

Max Activating Token Index: 748

Text #6

Max Range: 2.0683. Min Range: -2.0683

Max Act: 1.7998. Min Act: -0.0000

Data Index: 571747 (The Pile)

Max Activating Token Index: 571

Text #7

Max Range: 2.0683. Min Range: -2.0683

Max Act: 1.7137. Min Act: -0.0000

Data Index: 307622 (The Pile)

Max Activating Token Index: 973

Text #8

Max Range: 2.0683. Min Range: -2.0683

Max Act: 1.7929. Min Act: -0.0000

Data Index: 425225 (The Pile)

Max Activating Token Index: 265

Text #9

Max Range: 2.0683. Min Range: -2.0683

Max Act: 1.6652. Min Act: -0.0000

Data Index: 887368 (The Pile)

Max Activating Token Index: 802

Text #10

Max Range: 2.0683. Min Range: -2.0683

Max Act: 1.7405. Min Act: -0.0000

Data Index: 257860 (The Pile)

Max Activating Token Index: 758

Text #11

Max Range: 2.0683. Min Range: -2.0683

Max Act: 1.5459. Min Act: -0.0000

Data Index: 1266705 (The Pile)

Max Activating Token Index: 758

Text #12

Max Range: 2.0683. Min Range: -2.0683

Max Act: 1.6519. Min Act: -0.0000

Data Index: 1488570 (The Pile)

Max Activating Token Index: 593

Text #13

Max Range: 2.0683. Min Range: -2.0683

Max Act: 1.6447. Min Act: -0.0000

Data Index: 168542 (The Pile)

Max Activating Token Index: 644

Text #14

Max Range: 2.0683. Min Range: -2.0683

Max Act: 1.6065. Min Act: -0.0000

Data Index: 998490 (The Pile)

Max Activating Token Index: 968

Text #15

Max Range: 2.0683. Min Range: -2.0683

Max Act: 1.6308. Min Act: -0.0000

Data Index: 495161 (The Pile)

Max Activating Token Index: 37

Text #16

Max Range: 2.0683. Min Range: -2.0683

Max Act: 1.6046. Min Act: -0.0000

Data Index: 86665 (The Pile)

Max Activating Token Index: 472

Text #17

Max Range: 2.0683. Min Range: -2.0683

Max Act: 1.6484. Min Act: -0.0000

Data Index: 1900080 (The Pile)

Max Activating Token Index: 929

Text #18

Max Range: 2.0683. Min Range: -2.0683

Max Act: 1.6992. Min Act: -0.0000

Data Index: 1476923 (The Pile)

Max Activating Token Index: 642

Text #19

Max Range: 2.0683. Min Range: -2.0683

Max Act: 1.4191. Min Act: -0.0000

Data Index: 782769 (The Pile)

Max Activating Token Index: 772