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

Dataset: The Pile

Neuron 853 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.5955. Min Act: -0.0000

Data Index: 1238656 (The Pile)

Max Activating Token Index: 859

Text #1

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.5477. Min Act: -0.0000

Data Index: 1754253 (The Pile)

Max Activating Token Index: 463

Text #2

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.5269. Min Act: -0.0000

Data Index: 147752 (The Pile)

Max Activating Token Index: 482

Text #3

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.5222. Min Act: -0.0000

Data Index: 1729118 (The Pile)

Max Activating Token Index: 23

Text #4

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.5386. Min Act: -0.0000

Data Index: 1759988 (The Pile)

Max Activating Token Index: 804

Text #5

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4942. Min Act: -0.0000

Data Index: 1956474 (The Pile)

Max Activating Token Index: 518

Text #6

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4910. Min Act: -0.0000

Data Index: 1675454 (The Pile)

Max Activating Token Index: 507

Text #7

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4687. Min Act: -0.0000

Data Index: 316745 (The Pile)

Max Activating Token Index: 382

Text #8

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.5040. Min Act: -0.0000

Data Index: 1260157 (The Pile)

Max Activating Token Index: 700

Text #9

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4396. Min Act: -0.0000

Data Index: 532787 (The Pile)

Max Activating Token Index: 803

Text #10

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1081340 (The Pile)

Max Activating Token Index: 15

Text #11

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4633. Min Act: -0.0000

Data Index: 13306 (The Pile)

Max Activating Token Index: 440

Text #12

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4755. Min Act: -0.0000

Data Index: 728771 (The Pile)

Max Activating Token Index: 443

Text #13

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4461. Min Act: -0.0000

Data Index: 857895 (The Pile)

Max Activating Token Index: 38

Text #14

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4553. Min Act: -0.0000

Data Index: 1696231 (The Pile)

Max Activating Token Index: 158

Text #15

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1413344 (The Pile)

Max Activating Token Index: 393

Text #16

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4613. Min Act: -0.0000

Data Index: 963233 (The Pile)

Max Activating Token Index: 666

Text #17

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4374. Min Act: -0.0000

Data Index: 1486288 (The Pile)

Max Activating Token Index: 8

Text #18

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4422. Min Act: -0.0000

Data Index: 416052 (The Pile)

Max Activating Token Index: 1012

Text #19

Max Range: 0.5955. Min Range: -0.5955

Max Act: 0.4620. Min Act: -0.0000

Data Index: 1848788 (The Pile)

Max Activating Token Index: 491