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

Dataset: The Pile

Neuron 2118 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.6569. Min Act: -0.0000

Data Index: 425351 (The Pile)

Max Activating Token Index: 1004

Text #1

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.5322. Min Act: -0.0000

Data Index: 522071 (The Pile)

Max Activating Token Index: 730

Text #2

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.4789. Min Act: -0.0000

Data Index: 1619884 (The Pile)

Max Activating Token Index: 706

Text #3

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.3568. Min Act: -0.0000

Data Index: 1751248 (The Pile)

Max Activating Token Index: 324

Text #4

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.3052. Min Act: -0.0000

Data Index: 1526607 (The Pile)

Max Activating Token Index: 915

Text #5

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.1262. Min Act: -0.0000

Data Index: 13778 (The Pile)

Max Activating Token Index: 247

Text #6

Max Range: 3.6569. Min Range: -3.6569

Max Act: 2.9652. Min Act: -0.0000

Data Index: 1786195 (The Pile)

Max Activating Token Index: 813

Text #7

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.1023. Min Act: -0.0000

Data Index: 1808582 (The Pile)

Max Activating Token Index: 375

Text #8

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.3728. Min Act: -0.0000

Data Index: 131103 (The Pile)

Max Activating Token Index: 656

Text #9

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.3319. Min Act: -0.0000

Data Index: 1877955 (The Pile)

Max Activating Token Index: 258

Text #10

Max Range: 3.6569. Min Range: -3.6569

Max Act: 2.8856. Min Act: -0.0000

Data Index: 470043 (The Pile)

Max Activating Token Index: 485

Text #11

Max Range: 3.6569. Min Range: -3.6569

Max Act: 2.8803. Min Act: -0.0000

Data Index: 1562158 (The Pile)

Max Activating Token Index: 6

Text #12

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.1440. Min Act: -0.0000

Data Index: 1187701 (The Pile)

Max Activating Token Index: 160

Text #13

Max Range: 3.6569. Min Range: -3.6569

Max Act: 2.9773. Min Act: -0.0000

Data Index: 510635 (The Pile)

Max Activating Token Index: 439

Text #14

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.0406. Min Act: -0.0000

Data Index: 1940713 (The Pile)

Max Activating Token Index: 653

Text #15

Max Range: 3.6569. Min Range: -3.6569

Max Act: 2.7799. Min Act: -0.0000

Data Index: 1791926 (The Pile)

Max Activating Token Index: 423

Text #16

Max Range: 3.6569. Min Range: -3.6569

Max Act: 3.0694. Min Act: -0.0000

Data Index: 1320023 (The Pile)

Max Activating Token Index: 535

Text #17

Max Range: 3.6569. Min Range: -3.6569

Max Act: 2.7804. Min Act: -0.0000

Data Index: 49558 (The Pile)

Max Activating Token Index: 733

Text #18

Max Range: 3.6569. Min Range: -3.6569

Max Act: 2.7912. Min Act: -0.0000

Data Index: 1716748 (The Pile)

Max Activating Token Index: 29

Text #19

Max Range: 3.6569. Min Range: -3.6569

Max Act: 2.7442. Min Act: -0.0000

Data Index: 885187 (The Pile)

Max Activating Token Index: 236