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

Dataset: The Pile

Neuron 673 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: 3.9845. Min Range: -3.9845

Max Act: 3.9845. Min Act: -0.0000

Data Index: 1218971 (The Pile)

Max Activating Token Index: 643

Text #1

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.5285. Min Act: -0.0000

Data Index: 365144 (The Pile)

Max Activating Token Index: 857

Text #2

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.5948. Min Act: -0.0000

Data Index: 416095 (The Pile)

Max Activating Token Index: 697

Text #3

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.1966. Min Act: -0.0000

Data Index: 61486 (The Pile)

Max Activating Token Index: 833

Text #4

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.3285. Min Act: -0.0000

Data Index: 1981798 (The Pile)

Max Activating Token Index: 642

Text #5

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.1783. Min Act: -0.0000

Data Index: 780981 (The Pile)

Max Activating Token Index: 145

Text #6

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.2890. Min Act: -0.0000

Data Index: 1541747 (The Pile)

Max Activating Token Index: 641

Text #7

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.0766. Min Act: -0.0000

Data Index: 1184201 (The Pile)

Max Activating Token Index: 258

Text #8

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.1901. Min Act: -0.0000

Data Index: 1431007 (The Pile)

Max Activating Token Index: 409

Text #9

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.1802. Min Act: -0.0000

Data Index: 989461 (The Pile)

Max Activating Token Index: 101

Text #10

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.1941. Min Act: -0.0000

Data Index: 229373 (The Pile)

Max Activating Token Index: 168

Text #11

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.1671. Min Act: -0.0000

Data Index: 1529609 (The Pile)

Max Activating Token Index: 711

Text #12

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.1393. Min Act: -0.0000

Data Index: 726491 (The Pile)

Max Activating Token Index: 112

Text #13

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.1344. Min Act: -0.0000

Data Index: 349549 (The Pile)

Max Activating Token Index: 436

Text #14

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.1290. Min Act: -0.0000

Data Index: 1732988 (The Pile)

Max Activating Token Index: 498

Text #15

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.2355. Min Act: -0.0000

Data Index: 1647597 (The Pile)

Max Activating Token Index: 541

Text #16

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.0883. Min Act: -0.0000

Data Index: 537481 (The Pile)

Max Activating Token Index: 163

Text #17

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.2310. Min Act: -0.0000

Data Index: 605368 (The Pile)

Max Activating Token Index: 295

Text #18

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.0840. Min Act: -0.0000

Data Index: 826099 (The Pile)

Max Activating Token Index: 627

Text #19

Max Range: 3.9845. Min Range: -3.9845

Max Act: 3.0613. Min Act: -0.0000

Data Index: 562710 (The Pile)

Max Activating Token Index: 502