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

Dataset: The Pile

Neuron 499 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: 1.2443. Min Range: -1.2443

Max Act: 1.2443. Min Act: -0.0000

Data Index: 1455686 (The Pile)

Max Activating Token Index: 39

Text #1

Max Range: 1.2443. Min Range: -1.2443

Max Act: 1.1962. Min Act: -0.0000

Data Index: 152036 (The Pile)

Max Activating Token Index: 972

Text #2

Max Range: 1.2443. Min Range: -1.2443

Max Act: 1.1656. Min Act: -0.0000

Data Index: 1573740 (The Pile)

Max Activating Token Index: 882

Text #3

Max Range: 1.2443. Min Range: -1.2443

Max Act: 1.1947. Min Act: -0.0000

Data Index: 260610 (The Pile)

Max Activating Token Index: 760

Text #4

Max Range: 1.2443. Min Range: -1.2443

Max Act: 1.1833. Min Act: -0.0000

Data Index: 911175 (The Pile)

Max Activating Token Index: 76

Text #5

Max Range: 1.2443. Min Range: -1.2443

Max Act: 1.1673. Min Act: -0.0000

Data Index: 732952 (The Pile)

Max Activating Token Index: 972

Text #6

Max Range: 1.2443. Min Range: -1.2443

Max Act: 1.1984. Min Act: -0.0000

Data Index: 1768417 (The Pile)

Max Activating Token Index: 280

Text #7

Max Range: 1.2443. Min Range: -1.2443

Max Act: 1.1220. Min Act: -0.0000

Data Index: 1516149 (The Pile)

Max Activating Token Index: 190

Text #8

Max Range: 1.2443. Min Range: -1.2443

Max Act: 1.1497. Min Act: -0.0000

Data Index: 474613 (The Pile)

Max Activating Token Index: 307

Text #9

Max Range: 1.2443. Min Range: -1.2443

Max Act: 1.1499. Min Act: -0.0000

Data Index: 1581359 (The Pile)

Max Activating Token Index: 691

Text #10

Max Range: 1.2443. Min Range: -1.2443

Max Act: 1.0730. Min Act: -0.0000

Data Index: 240372 (The Pile)

Max Activating Token Index: 909

Text #11

Max Range: 1.2443. Min Range: -1.2443

Max Act: 1.0750. Min Act: -0.0000

Data Index: 430854 (The Pile)

Max Activating Token Index: 857

Text #12

Max Range: 1.2443. Min Range: -1.2443

Max Act: 0.9451. Min Act: -0.0000

Data Index: 1205594 (The Pile)

Max Activating Token Index: 698

Text #13

Max Range: 1.2443. Min Range: -1.2443

Max Act: 1.0926. Min Act: -0.0000

Data Index: 17855 (The Pile)

Max Activating Token Index: 708

Text #14

Max Range: 1.2443. Min Range: -1.2443

Max Act: 0.9760. Min Act: -0.0000

Data Index: 85397 (The Pile)

Max Activating Token Index: 370

Text #15

Max Range: 1.2443. Min Range: -1.2443

Max Act: 0.9794. Min Act: -0.0000

Data Index: 288837 (The Pile)

Max Activating Token Index: 93

Text #16

Max Range: 1.2443. Min Range: -1.2443

Max Act: 1.1540. Min Act: -0.0000

Data Index: 1442882 (The Pile)

Max Activating Token Index: 300

Text #17

Max Range: 1.2443. Min Range: -1.2443

Max Act: 1.0783. Min Act: -0.0000

Data Index: 837153 (The Pile)

Max Activating Token Index: 384

Text #18

Max Range: 1.2443. Min Range: -1.2443

Max Act: 0.9869. Min Act: -0.0000

Data Index: 711558 (The Pile)

Max Activating Token Index: 867

Text #19

Max Range: 1.2443. Min Range: -1.2443

Max Act: 1.0501. Min Act: -0.0000

Data Index: 1017355 (The Pile)

Max Activating Token Index: 63