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

Dataset: The Pile

Neuron 4171 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: 5.1637. Min Range: -5.1637

Max Act: 5.1637. Min Act: -0.0000

Data Index: 1359058 (The Pile)

Max Activating Token Index: 844

Text #1

Max Range: 5.1637. Min Range: -5.1637

Max Act: 4.9711. Min Act: -0.0000

Data Index: 865450 (The Pile)

Max Activating Token Index: 848

Text #2

Max Range: 5.1637. Min Range: -5.1637

Max Act: 4.4604. Min Act: -0.0000

Data Index: 355034 (The Pile)

Max Activating Token Index: 852

Text #3

Max Range: 5.1637. Min Range: -5.1637

Max Act: 3.8867. Min Act: -0.0000

Data Index: 1408717 (The Pile)

Max Activating Token Index: 568

Text #4

Max Range: 5.1637. Min Range: -5.1637

Max Act: 3.6823. Min Act: -0.0000

Data Index: 1513371 (The Pile)

Max Activating Token Index: 274

Text #5

Max Range: 5.1637. Min Range: -5.1637

Max Act: 3.7942. Min Act: -0.0000

Data Index: 362632 (The Pile)

Max Activating Token Index: 850

Text #6

Max Range: 5.1637. Min Range: -5.1637

Max Act: 3.2847. Min Act: -0.0000

Data Index: 185761 (The Pile)

Max Activating Token Index: 159

Text #7

Max Range: 5.1637. Min Range: -5.1637

Max Act: 3.4381. Min Act: -0.0000

Data Index: 1992147 (The Pile)

Max Activating Token Index: 303

Text #8

Max Range: 5.1637. Min Range: -5.1637

Max Act: 3.5110. Min Act: -0.0000

Data Index: 1433247 (The Pile)

Max Activating Token Index: 212

Text #9

Max Range: 5.1637. Min Range: -5.1637

Max Act: 2.8830. Min Act: -0.0000

Data Index: 1229640 (The Pile)

Max Activating Token Index: 151

Text #10

Max Range: 5.1637. Min Range: -5.1637

Max Act: 3.3829. Min Act: -0.0000

Data Index: 1479647 (The Pile)

Max Activating Token Index: 338

Text #11

Max Range: 5.1637. Min Range: -5.1637

Max Act: 2.9056. Min Act: -0.0000

Data Index: 668007 (The Pile)

Max Activating Token Index: 540

Text #12

Max Range: 5.1637. Min Range: -5.1637

Max Act: 2.7150. Min Act: -0.0000

Data Index: 1903900 (The Pile)

Max Activating Token Index: 714

Text #13

Max Range: 5.1637. Min Range: -5.1637

Max Act: 2.9835. Min Act: -0.0000

Data Index: 228580 (The Pile)

Max Activating Token Index: 584

Text #14

Max Range: 5.1637. Min Range: -5.1637

Max Act: 3.0881. Min Act: -0.0000

Data Index: 296806 (The Pile)

Max Activating Token Index: 522

Text #15

Max Range: 5.1637. Min Range: -5.1637

Max Act: 2.9534. Min Act: -0.0000

Data Index: 340312 (The Pile)

Max Activating Token Index: 404

Text #16

Max Range: 5.1637. Min Range: -5.1637

Max Act: 3.7912. Min Act: -0.0000

Data Index: 1407491 (The Pile)

Max Activating Token Index: 878

Text #17

Max Range: 5.1637. Min Range: -5.1637

Max Act: 2.9833. Min Act: -0.0000

Data Index: 1059169 (The Pile)

Max Activating Token Index: 488

Text #18

Max Range: 5.1637. Min Range: -5.1637

Max Act: 3.0850. Min Act: -0.0000

Data Index: 1599340 (The Pile)

Max Activating Token Index: 711

Text #19

Max Range: 5.1637. Min Range: -5.1637

Max Act: 3.1155. Min Act: -0.0000

Data Index: 1110988 (The Pile)

Max Activating Token Index: 654