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

Dataset: The Pile

Neuron 786 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: 0.7305. Min Range: -0.7305

Max Act: 0.6892. Min Act: -0.0000

Data Index: 15273 (The Pile)

Max Activating Token Index: 777

Text #1

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.7072. Min Act: -0.0000

Data Index: 920039 (The Pile)

Max Activating Token Index: 847

Text #2

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.7305. Min Act: -0.0000

Data Index: 643514 (The Pile)

Max Activating Token Index: 415

Text #3

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1170785 (The Pile)

Max Activating Token Index: 883

Text #4

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.6869. Min Act: -0.0000

Data Index: 1990668 (The Pile)

Max Activating Token Index: 691

Text #5

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.6839. Min Act: -0.0000

Data Index: 13608 (The Pile)

Max Activating Token Index: 318

Text #6

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.6265. Min Act: -0.0000

Data Index: 374369 (The Pile)

Max Activating Token Index: 630

Text #7

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.6062. Min Act: -0.0000

Data Index: 925457 (The Pile)

Max Activating Token Index: 310

Text #8

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1888307 (The Pile)

Max Activating Token Index: 891

Text #9

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.6275. Min Act: -0.0000

Data Index: 71348 (The Pile)

Max Activating Token Index: 379

Text #10

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1773529 (The Pile)

Max Activating Token Index: 521

Text #11

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.6089. Min Act: -0.0000

Data Index: 47018 (The Pile)

Max Activating Token Index: 65

Text #12

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.5976. Min Act: -0.0000

Data Index: 1663396 (The Pile)

Max Activating Token Index: 654

Text #13

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.6349. Min Act: -0.0000

Data Index: 1097132 (The Pile)

Max Activating Token Index: 705

Text #14

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.5764. Min Act: -0.0000

Data Index: 1823751 (The Pile)

Max Activating Token Index: 1000

Text #15

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.5900. Min Act: -0.0000

Data Index: 657538 (The Pile)

Max Activating Token Index: 1000

Text #16

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.5655. Min Act: -0.0000

Data Index: 1982112 (The Pile)

Max Activating Token Index: 630

Text #17

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.6170. Min Act: -0.0000

Data Index: 270601 (The Pile)

Max Activating Token Index: 642

Text #18

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.5869. Min Act: -0.0000

Data Index: 646776 (The Pile)

Max Activating Token Index: 48

Text #19

Max Range: 0.7305. Min Range: -0.7305

Max Act: 0.5651. Min Act: -0.0000

Data Index: 1014237 (The Pile)

Max Activating Token Index: 553