Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3514 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.8282. Min Act: -0.0000

Data Index: 975863 (The Pile)

Max Activating Token Index: 874

Text #1

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.8934. Min Act: -0.0000

Data Index: 594367 (The Pile)

Max Activating Token Index: 759

Text #2

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.9084. Min Act: -0.0000

Data Index: 351980 (The Pile)

Max Activating Token Index: 26

Text #3

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6634. Min Act: -0.0000

Data Index: 945568 (The Pile)

Max Activating Token Index: 615

Text #4

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1530716 (The Pile)

Max Activating Token Index: 188

Text #5

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7273. Min Act: -0.0000

Data Index: 1480512 (The Pile)

Max Activating Token Index: 19

Text #6

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7106. Min Act: -0.0000

Data Index: 982285 (The Pile)

Max Activating Token Index: 927

Text #7

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6419. Min Act: -0.0000

Data Index: 1279240 (The Pile)

Max Activating Token Index: 750

Text #8

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6790. Min Act: -0.0000

Data Index: 278284 (The Pile)

Max Activating Token Index: 968

Text #9

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6757. Min Act: -0.0000

Data Index: 906049 (The Pile)

Max Activating Token Index: 767

Text #10

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6468. Min Act: -0.0000

Data Index: 1857458 (The Pile)

Max Activating Token Index: 637

Text #11

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7021. Min Act: -0.0000

Data Index: 443974 (The Pile)

Max Activating Token Index: 716

Text #12

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.7400. Min Act: -0.0000

Data Index: 1846536 (The Pile)

Max Activating Token Index: 462

Text #13

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6436. Min Act: -0.0000

Data Index: 721497 (The Pile)

Max Activating Token Index: 331

Text #14

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6212. Min Act: -0.0000

Data Index: 345357 (The Pile)

Max Activating Token Index: 221

Text #15

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.5464. Min Act: -0.0000

Data Index: 269246 (The Pile)

Max Activating Token Index: 756

Text #16

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.5795. Min Act: -0.0000

Data Index: 1477888 (The Pile)

Max Activating Token Index: 800

Text #17

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.6566. Min Act: -0.0000

Data Index: 1798227 (The Pile)

Max Activating Token Index: 976

Text #18

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.5703. Min Act: -0.0000

Data Index: 1621816 (The Pile)

Max Activating Token Index: 187

Text #19

Max Range: 0.9084. Min Range: -0.9084

Max Act: 0.5918. Min Act: -0.0000

Data Index: 1879331 (The Pile)

Max Activating Token Index: 740