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

Dataset: The Pile

Neuron 2792 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: 1.1044. Min Range: -1.1044

Max Act: 1.1044. Min Act: -0.0000

Data Index: 496698 (The Pile)

Max Activating Token Index: 750

Text #1

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.9335. Min Act: -0.0000

Data Index: 1309783 (The Pile)

Max Activating Token Index: 1013

Text #2

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.9333. Min Act: -0.0000

Data Index: 1481404 (The Pile)

Max Activating Token Index: 942

Text #3

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.9760. Min Act: -0.0000

Data Index: 333473 (The Pile)

Max Activating Token Index: 390

Text #4

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.9389. Min Act: -0.0000

Data Index: 463764 (The Pile)

Max Activating Token Index: 405

Text #5

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.8258. Min Act: -0.0000

Data Index: 1031989 (The Pile)

Max Activating Token Index: 512

Text #6

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.9001. Min Act: -0.0000

Data Index: 280400 (The Pile)

Max Activating Token Index: 998

Text #7

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.8640. Min Act: -0.0000

Data Index: 1704364 (The Pile)

Max Activating Token Index: 298

Text #8

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.9748. Min Act: -0.0000

Data Index: 1020864 (The Pile)

Max Activating Token Index: 698

Text #9

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.7861. Min Act: -0.0000

Data Index: 1331130 (The Pile)

Max Activating Token Index: 349

Text #10

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.8462. Min Act: -0.0000

Data Index: 228427 (The Pile)

Max Activating Token Index: 399

Text #11

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.8367. Min Act: -0.0000

Data Index: 958019 (The Pile)

Max Activating Token Index: 337

Text #12

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.8511. Min Act: -0.0000

Data Index: 1101297 (The Pile)

Max Activating Token Index: 989

Text #13

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.7535. Min Act: -0.0000

Data Index: 1243896 (The Pile)

Max Activating Token Index: 507

Text #14

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.7756. Min Act: -0.0000

Data Index: 658380 (The Pile)

Max Activating Token Index: 608

Text #15

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.8391. Min Act: -0.0000

Data Index: 1825093 (The Pile)

Max Activating Token Index: 361

Text #16

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.8195. Min Act: -0.0000

Data Index: 1707074 (The Pile)

Max Activating Token Index: 147

Text #17

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.7942. Min Act: -0.0000

Data Index: 1441554 (The Pile)

Max Activating Token Index: 595

Text #18

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.6635. Min Act: -0.0000

Data Index: 90460 (The Pile)

Max Activating Token Index: 621

Text #19

Max Range: 1.1044. Min Range: -1.1044

Max Act: 0.6873. Min Act: -0.0000

Data Index: 563127 (The Pile)

Max Activating Token Index: 989