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

Dataset: The Pile

Neuron 331 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.2102. Min Act: -0.0000

Data Index: 72685 (The Pile)

Max Activating Token Index: 445

Text #1

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.2044. Min Act: -0.0000

Data Index: 1970542 (The Pile)

Max Activating Token Index: 850

Text #2

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1804. Min Act: -0.0000

Data Index: 71603 (The Pile)

Max Activating Token Index: 823

Text #3

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1797. Min Act: -0.0000

Data Index: 1105904 (The Pile)

Max Activating Token Index: 333

Text #4

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1860. Min Act: -0.0000

Data Index: 901222 (The Pile)

Max Activating Token Index: 363

Text #5

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1194168 (The Pile)

Max Activating Token Index: 181

Text #6

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.2049. Min Act: -0.0000

Data Index: 614941 (The Pile)

Max Activating Token Index: 529

Text #7

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1520254 (The Pile)

Max Activating Token Index: 699

Text #8

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1603. Min Act: -0.0000

Data Index: 1941130 (The Pile)

Max Activating Token Index: 905

Text #9

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1761. Min Act: -0.0000

Data Index: 1819602 (The Pile)

Max Activating Token Index: 465

Text #10

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1727. Min Act: -0.0000

Data Index: 948246 (The Pile)

Max Activating Token Index: 10

Text #11

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1703. Min Act: -0.0000

Data Index: 1499642 (The Pile)

Max Activating Token Index: 68

Text #12

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1643. Min Act: -0.0000

Data Index: 93724 (The Pile)

Max Activating Token Index: 747

Text #13

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1757. Min Act: -0.0000

Data Index: 1725625 (The Pile)

Max Activating Token Index: 223

Text #14

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1579. Min Act: -0.0000

Data Index: 230346 (The Pile)

Max Activating Token Index: 378

Text #15

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1561. Min Act: -0.0000

Data Index: 1036369 (The Pile)

Max Activating Token Index: 972

Text #16

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1529. Min Act: -0.0000

Data Index: 208182 (The Pile)

Max Activating Token Index: 379

Text #17

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1533. Min Act: -0.0000

Data Index: 387892 (The Pile)

Max Activating Token Index: 329

Text #18

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1638. Min Act: -0.0000

Data Index: 410332 (The Pile)

Max Activating Token Index: 458

Text #19

Max Range: 0.2102. Min Range: -0.2102

Max Act: 0.1532. Min Act: -0.0000

Data Index: 1594261 (The Pile)

Max Activating Token Index: 186