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

Dataset: The Pile

Neuron 1252 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.4683. Min Act: -0.0000

Data Index: 910181 (The Pile)

Max Activating Token Index: 742

Text #1

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.1877. Min Act: -0.0000

Data Index: 1395567 (The Pile)

Max Activating Token Index: 170

Text #2

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.0983. Min Act: -0.0000

Data Index: 111023 (The Pile)

Max Activating Token Index: 323

Text #3

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.1106. Min Act: -0.0000

Data Index: 1010515 (The Pile)

Max Activating Token Index: 833

Text #4

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.1633. Min Act: -0.0000

Data Index: 1959002 (The Pile)

Max Activating Token Index: 614

Text #5

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.1481. Min Act: -0.0000

Data Index: 1470568 (The Pile)

Max Activating Token Index: 939

Text #6

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.1498. Min Act: -0.0000

Data Index: 1499352 (The Pile)

Max Activating Token Index: 715

Text #7

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.0588. Min Act: -0.0000

Data Index: 315446 (The Pile)

Max Activating Token Index: 281

Text #8

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.0791. Min Act: -0.0000

Data Index: 1455041 (The Pile)

Max Activating Token Index: 8

Text #9

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.1039. Min Act: -0.0000

Data Index: 1421662 (The Pile)

Max Activating Token Index: 487

Text #10

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.1903. Min Act: -0.0000

Data Index: 1682145 (The Pile)

Max Activating Token Index: 940

Text #11

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.0145. Min Act: -0.0000

Data Index: 844660 (The Pile)

Max Activating Token Index: 603

Text #12

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.0739. Min Act: -0.0000

Data Index: 1340397 (The Pile)

Max Activating Token Index: 676

Text #13

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.0767. Min Act: -0.0000

Data Index: 53008 (The Pile)

Max Activating Token Index: 200

Text #14

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.0397. Min Act: -0.0000

Data Index: 1794915 (The Pile)

Max Activating Token Index: 260

Text #15

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.0323. Min Act: -0.0000

Data Index: 1238708 (The Pile)

Max Activating Token Index: 921

Text #16

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.0945. Min Act: -0.0000

Data Index: 1588062 (The Pile)

Max Activating Token Index: 24

Text #17

Max Range: 1.4683. Min Range: -1.4683

Max Act: 1.0297. Min Act: -0.0000

Data Index: 948153 (The Pile)

Max Activating Token Index: 788

Text #18

Max Range: 1.4683. Min Range: -1.4683

Max Act: 0.9885. Min Act: -0.0000

Data Index: 325048 (The Pile)

Max Activating Token Index: 589

Text #19

Max Range: 1.4683. Min Range: -1.4683

Max Act: 0.9803. Min Act: -0.0000

Data Index: 1111947 (The Pile)

Max Activating Token Index: 72