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

Dataset: The Pile

Neuron 3498 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.6555. Min Act: -0.0000

Data Index: 588931 (The Pile)

Max Activating Token Index: 113

Text #1

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.3672. Min Act: -0.0000

Data Index: 635544 (The Pile)

Max Activating Token Index: 584

Text #2

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.4688. Min Act: -0.0000

Data Index: 834636 (The Pile)

Max Activating Token Index: 824

Text #3

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.4283. Min Act: -0.0000

Data Index: 680470 (The Pile)

Max Activating Token Index: 473

Text #4

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.3401. Min Act: -0.0000

Data Index: 607177 (The Pile)

Max Activating Token Index: 146

Text #5

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.3442. Min Act: -0.0000

Data Index: 217019 (The Pile)

Max Activating Token Index: 522

Text #6

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.4631. Min Act: -0.0000

Data Index: 393087 (The Pile)

Max Activating Token Index: 865

Text #7

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.3023. Min Act: -0.0000

Data Index: 1230449 (The Pile)

Max Activating Token Index: 262

Text #8

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.2184. Min Act: -0.0000

Data Index: 926323 (The Pile)

Max Activating Token Index: 139

Text #9

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.3472. Min Act: -0.0000

Data Index: 335970 (The Pile)

Max Activating Token Index: 250

Text #10

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.3178. Min Act: -0.0000

Data Index: 1982449 (The Pile)

Max Activating Token Index: 252

Text #11

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.2567. Min Act: -0.0000

Data Index: 858979 (The Pile)

Max Activating Token Index: 836

Text #12

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.0989. Min Act: -0.0000

Data Index: 1649946 (The Pile)

Max Activating Token Index: 876

Text #13

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.2410. Min Act: -0.0000

Data Index: 1930898 (The Pile)

Max Activating Token Index: 822

Text #14

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.1643. Min Act: -0.0000

Data Index: 378247 (The Pile)

Max Activating Token Index: 842

Text #15

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.1374. Min Act: -0.0000

Data Index: 299405 (The Pile)

Max Activating Token Index: 377

Text #16

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.1180. Min Act: -0.0000

Data Index: 1756927 (The Pile)

Max Activating Token Index: 675

Text #17

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.1290. Min Act: -0.0000

Data Index: 1612052 (The Pile)

Max Activating Token Index: 673

Text #18

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.0613. Min Act: -0.0000

Data Index: 1250518 (The Pile)

Max Activating Token Index: 518

Text #19

Max Range: 1.6555. Min Range: -1.6555

Max Act: 1.1609. Min Act: -0.0000

Data Index: 1106962 (The Pile)

Max Activating Token Index: 191