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

Dataset: The Pile

Neuron 2273 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: 5.3970. Min Range: -5.3970

Max Act: 5.3970. Min Act: -0.0000

Data Index: 978847 (The Pile)

Max Activating Token Index: 578

Text #1

Max Range: 5.3970. Min Range: -5.3970

Max Act: 5.1822. Min Act: -0.0000

Data Index: 1531947 (The Pile)

Max Activating Token Index: 622

Text #2

Max Range: 5.3970. Min Range: -5.3970

Max Act: 5.0690. Min Act: -0.0000

Data Index: 1736119 (The Pile)

Max Activating Token Index: 900

Text #3

Max Range: 5.3970. Min Range: -5.3970

Max Act: 5.2164. Min Act: -0.0000

Data Index: 127487 (The Pile)

Max Activating Token Index: 615

Text #4

Max Range: 5.3970. Min Range: -5.3970

Max Act: 4.8782. Min Act: -0.0000

Data Index: 1902085 (The Pile)

Max Activating Token Index: 136

Text #5

Max Range: 5.3970. Min Range: -5.3970

Max Act: 4.9736. Min Act: -0.0000

Data Index: 316663 (The Pile)

Max Activating Token Index: 112

Text #6

Max Range: 5.3970. Min Range: -5.3970

Max Act: 4.4814. Min Act: -0.0000

Data Index: 1716575 (The Pile)

Max Activating Token Index: 781

Text #7

Max Range: 5.3970. Min Range: -5.3970

Max Act: 4.8211. Min Act: -0.0000

Data Index: 1691706 (The Pile)

Max Activating Token Index: 461

Text #8

Max Range: 5.3970. Min Range: -5.3970

Max Act: 4.6265. Min Act: -0.0000

Data Index: 1105980 (The Pile)

Max Activating Token Index: 613

Text #9

Max Range: 5.3970. Min Range: -5.3970

Max Act: 3.9963. Min Act: -0.0000

Data Index: 1802472 (The Pile)

Max Activating Token Index: 678

Text #10

Max Range: 5.3970. Min Range: -5.3970

Max Act: 4.4919. Min Act: -0.0000

Data Index: 422156 (The Pile)

Max Activating Token Index: 457

Text #11

Max Range: 5.3970. Min Range: -5.3970

Max Act: 4.3100. Min Act: -0.0000

Data Index: 1441864 (The Pile)

Max Activating Token Index: 443

Text #12

Max Range: 5.3970. Min Range: -5.3970

Max Act: 4.3614. Min Act: -0.0000

Data Index: 1890081 (The Pile)

Max Activating Token Index: 667

Text #13

Max Range: 5.3970. Min Range: -5.3970

Max Act: 4.3342. Min Act: -0.0000

Data Index: 1697240 (The Pile)

Max Activating Token Index: 819

Text #14

Max Range: 5.3970. Min Range: -5.3970

Max Act: 4.1798. Min Act: -0.0000

Data Index: 1981650 (The Pile)

Max Activating Token Index: 1021

Text #15

Max Range: 5.3970. Min Range: -5.3970

Max Act: 3.9857. Min Act: -0.0000

Data Index: 890854 (The Pile)

Max Activating Token Index: 876

Text #16

Max Range: 5.3970. Min Range: -5.3970

Max Act: 4.3096. Min Act: -0.0000

Data Index: 324866 (The Pile)

Max Activating Token Index: 685

Text #17

Max Range: 5.3970. Min Range: -5.3970

Max Act: 4.1143. Min Act: -0.0000

Data Index: 87496 (The Pile)

Max Activating Token Index: 450

Text #18

Max Range: 5.3970. Min Range: -5.3970

Max Act: 3.9477. Min Act: -0.0000

Data Index: 1271373 (The Pile)

Max Activating Token Index: 546

Text #19

Max Range: 5.3970. Min Range: -5.3970

Max Act: 4.2697. Min Act: -0.0000

Data Index: 1277159 (The Pile)

Max Activating Token Index: 698