Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2648 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.8028. Min Act: -0.0000

Data Index: 1138505 (The Pile)

Max Activating Token Index: 521

Text #1

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.6373. Min Act: -0.0000

Data Index: 774138 (The Pile)

Max Activating Token Index: 927

Text #2

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.6059. Min Act: -0.0000

Data Index: 211076 (The Pile)

Max Activating Token Index: 928

Text #3

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.6483. Min Act: -0.0000

Data Index: 509969 (The Pile)

Max Activating Token Index: 841

Text #4

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.6010. Min Act: -0.0000

Data Index: 1373674 (The Pile)

Max Activating Token Index: 65

Text #5

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.5915. Min Act: -0.0000

Data Index: 1592126 (The Pile)

Max Activating Token Index: 261

Text #6

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.6699. Min Act: -0.0000

Data Index: 575786 (The Pile)

Max Activating Token Index: 993

Text #7

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.4993. Min Act: -0.0000

Data Index: 216859 (The Pile)

Max Activating Token Index: 288

Text #8

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.4946. Min Act: -0.0000

Data Index: 518353 (The Pile)

Max Activating Token Index: 850

Text #9

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.3602. Min Act: -0.0000

Data Index: 1371808 (The Pile)

Max Activating Token Index: 761

Text #10

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.3986. Min Act: -0.0000

Data Index: 767418 (The Pile)

Max Activating Token Index: 629

Text #11

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.4093. Min Act: -0.0000

Data Index: 1727239 (The Pile)

Max Activating Token Index: 668

Text #12

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.5230. Min Act: -0.0000

Data Index: 345655 (The Pile)

Max Activating Token Index: 903

Text #13

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.3686. Min Act: -0.0000

Data Index: 162274 (The Pile)

Max Activating Token Index: 704

Text #14

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.4647. Min Act: -0.0000

Data Index: 1324523 (The Pile)

Max Activating Token Index: 942

Text #15

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.3678. Min Act: -0.0000

Data Index: 1411623 (The Pile)

Max Activating Token Index: 855

Text #16

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.4499. Min Act: -0.0000

Data Index: 315059 (The Pile)

Max Activating Token Index: 963

Text #17

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.2843. Min Act: -0.0000

Data Index: 291534 (The Pile)

Max Activating Token Index: 487

Text #18

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.3339. Min Act: -0.0000

Data Index: 625458 (The Pile)

Max Activating Token Index: 604

Text #19

Max Range: 1.8028. Min Range: -1.8028

Max Act: 1.2516. Min Act: -0.0000

Data Index: 737857 (The Pile)

Max Activating Token Index: 808