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

Dataset: The Pile

Neuron 4015 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: 3.0534. Min Range: -3.0534

Max Act: 3.0534. Min Act: -0.0000

Data Index: 1205461 (The Pile)

Max Activating Token Index: 483

Text #1

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.6505. Min Act: -0.0000

Data Index: 1865037 (The Pile)

Max Activating Token Index: 794

Text #2

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.6526. Min Act: -0.0000

Data Index: 1404076 (The Pile)

Max Activating Token Index: 577

Text #3

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.5163. Min Act: -0.0000

Data Index: 1612298 (The Pile)

Max Activating Token Index: 907

Text #4

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.3867. Min Act: -0.0000

Data Index: 1710555 (The Pile)

Max Activating Token Index: 23

Text #5

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.1503. Min Act: -0.0000

Data Index: 1168885 (The Pile)

Max Activating Token Index: 15

Text #6

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.2064. Min Act: -0.0000

Data Index: 1459363 (The Pile)

Max Activating Token Index: 12

Text #7

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.0945. Min Act: -0.0000

Data Index: 1658250 (The Pile)

Max Activating Token Index: 13

Text #8

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.4034. Min Act: -0.0000

Data Index: 1133479 (The Pile)

Max Activating Token Index: 665

Text #9

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.1598. Min Act: -0.0000

Data Index: 749349 (The Pile)

Max Activating Token Index: 351

Text #10

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.2744. Min Act: -0.0000

Data Index: 1564195 (The Pile)

Max Activating Token Index: 468

Text #11

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.1093. Min Act: -0.0000

Data Index: 974893 (The Pile)

Max Activating Token Index: 3

Text #12

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.1093. Min Act: -0.0000

Data Index: 1492880 (The Pile)

Max Activating Token Index: 3

Text #13

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.0961. Min Act: -0.0000

Data Index: 1929120 (The Pile)

Max Activating Token Index: 481

Text #14

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.0931. Min Act: -0.0000

Data Index: 1142761 (The Pile)

Max Activating Token Index: 333

Text #15

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.1556. Min Act: -0.0000

Data Index: 1360460 (The Pile)

Max Activating Token Index: 824

Text #16

Max Range: 3.0534. Min Range: -3.0534

Max Act: 1.8154. Min Act: -0.0000

Data Index: 898951 (The Pile)

Max Activating Token Index: 718

Text #17

Max Range: 3.0534. Min Range: -3.0534

Max Act: 1.9085. Min Act: -0.0000

Data Index: 864262 (The Pile)

Max Activating Token Index: 436

Text #18

Max Range: 3.0534. Min Range: -3.0534

Max Act: 2.0084. Min Act: -0.0000

Data Index: 1154375 (The Pile)

Max Activating Token Index: 42

Text #19

Max Range: 3.0534. Min Range: -3.0534

Max Act: 1.9578. Min Act: -0.0000

Data Index: 1220632 (The Pile)

Max Activating Token Index: 384