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

Dataset: The Pile

Neuron 588 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.4149. Min Range: -6.4149

Max Act: 5.8489. Min Act: -0.0000

Data Index: 1511645 (The Pile)

Max Activating Token Index: 127

Text #1

Max Range: 6.4149. Min Range: -6.4149

Max Act: 6.0598. Min Act: -0.0000

Data Index: 1061151 (The Pile)

Max Activating Token Index: 45

Text #2

Max Range: 6.4149. Min Range: -6.4149

Max Act: 6.4149. Min Act: -0.0000

Data Index: 1166725 (The Pile)

Max Activating Token Index: 336

Text #3

Max Range: 6.4149. Min Range: -6.4149

Max Act: 6.1964. Min Act: -0.0000

Data Index: 1851789 (The Pile)

Max Activating Token Index: 819

Text #4

Max Range: 6.4149. Min Range: -6.4149

Max Act: 5.8157. Min Act: -0.0000

Data Index: 754705 (The Pile)

Max Activating Token Index: 39

Text #5

Max Range: 6.4149. Min Range: -6.4149

Max Act: 5.5570. Min Act: -0.0000

Data Index: 1656619 (The Pile)

Max Activating Token Index: 469

Text #6

Max Range: 6.4149. Min Range: -6.4149

Max Act: 5.8977. Min Act: -0.0000

Data Index: 1860181 (The Pile)

Max Activating Token Index: 449

Text #7

Max Range: 6.4149. Min Range: -6.4149

Max Act: 5.5370. Min Act: -0.0000

Data Index: 79698 (The Pile)

Max Activating Token Index: 517

Text #8

Max Range: 6.4149. Min Range: -6.4149

Max Act: 5.6851. Min Act: -0.0000

Data Index: 1762088 (The Pile)

Max Activating Token Index: 276

Text #9

Max Range: 6.4149. Min Range: -6.4149

Max Act: 5.4661. Min Act: -0.0000

Data Index: 899295 (The Pile)

Max Activating Token Index: 455

Text #10

Max Range: 6.4149. Min Range: -6.4149

Max Act: 5.6665. Min Act: -0.0000

Data Index: 163775 (The Pile)

Max Activating Token Index: 519

Text #11

Max Range: 6.4149. Min Range: -6.4149

Max Act: 5.5094. Min Act: -0.0000

Data Index: 291120 (The Pile)

Max Activating Token Index: 462

Text #12

Max Range: 6.4149. Min Range: -6.4149

Max Act: 5.3227. Min Act: -0.0000

Data Index: 410849 (The Pile)

Max Activating Token Index: 148

Text #13

Max Range: 6.4149. Min Range: -6.4149

Max Act: 5.1454. Min Act: -0.0000

Data Index: 502021 (The Pile)

Max Activating Token Index: 249

Text #14

Max Range: 6.4149. Min Range: -6.4149

Max Act: 5.5284. Min Act: -0.0000

Data Index: 70736 (The Pile)

Max Activating Token Index: 52

Text #15

Max Range: 6.4149. Min Range: -6.4149

Max Act: 5.2335. Min Act: -0.0000

Data Index: 1831978 (The Pile)

Max Activating Token Index: 634

Text #16

Max Range: 6.4149. Min Range: -6.4149

Max Act: 5.3831. Min Act: -0.0000

Data Index: 1960608 (The Pile)

Max Activating Token Index: 350

Text #17

Max Range: 6.4149. Min Range: -6.4149

Max Act: 5.2970. Min Act: -0.0000

Data Index: 556384 (The Pile)

Max Activating Token Index: 726

Text #18

Max Range: 6.4149. Min Range: -6.4149

Max Act: 5.4394. Min Act: -0.0000

Data Index: 493983 (The Pile)

Max Activating Token Index: 247

Text #19

Max Range: 6.4149. Min Range: -6.4149

Max Act: 5.4703. Min Act: -0.0000

Data Index: 1035232 (The Pile)

Max Activating Token Index: 336