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

Dataset: The Pile

Neuron 1831 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6689. Min Act: -0.0000

Data Index: 1740299 (The Pile)

Max Activating Token Index: 907

Text #1

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6148. Min Act: -0.0000

Data Index: 285920 (The Pile)

Max Activating Token Index: 463

Text #2

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5882. Min Act: -0.0000

Data Index: 246574 (The Pile)

Max Activating Token Index: 533

Text #3

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1229233 (The Pile)

Max Activating Token Index: 931

Text #4

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5454. Min Act: -0.0000

Data Index: 1752595 (The Pile)

Max Activating Token Index: 748

Text #5

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5422. Min Act: -0.0000

Data Index: 185694 (The Pile)

Max Activating Token Index: 352

Text #6

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5495. Min Act: -0.0000

Data Index: 1005868 (The Pile)

Max Activating Token Index: 547

Text #7

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5399. Min Act: -0.0000

Data Index: 258949 (The Pile)

Max Activating Token Index: 220

Text #8

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5355. Min Act: -0.0000

Data Index: 489371 (The Pile)

Max Activating Token Index: 41

Text #9

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5303. Min Act: -0.0000

Data Index: 707477 (The Pile)

Max Activating Token Index: 871

Text #10

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5231. Min Act: -0.0000

Data Index: 877058 (The Pile)

Max Activating Token Index: 315

Text #11

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4871. Min Act: -0.0000

Data Index: 1458108 (The Pile)

Max Activating Token Index: 517

Text #12

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4957. Min Act: -0.0000

Data Index: 1153277 (The Pile)

Max Activating Token Index: 185

Text #13

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5058. Min Act: -0.0000

Data Index: 394762 (The Pile)

Max Activating Token Index: 673

Text #14

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4961. Min Act: -0.0000

Data Index: 1543021 (The Pile)

Max Activating Token Index: 650

Text #15

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4980. Min Act: -0.0000

Data Index: 1817763 (The Pile)

Max Activating Token Index: 1019

Text #16

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4783. Min Act: -0.0000

Data Index: 1426174 (The Pile)

Max Activating Token Index: 115

Text #17

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4941. Min Act: -0.0000

Data Index: 555457 (The Pile)

Max Activating Token Index: 122

Text #18

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4875. Min Act: 0.0000

Data Index: 725695 (The Pile)

Max Activating Token Index: 368

Text #19

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4818. Min Act: -0.0000

Data Index: 1407202 (The Pile)

Max Activating Token Index: 790