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

Dataset: The Pile

Neuron 2553 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: 0.5224. Min Range: -0.5224

Max Act: 0.5224. Min Act: -0.0000

Data Index: 1790135 (The Pile)

Max Activating Token Index: 933

Text #1

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4406. Min Act: -0.0000

Data Index: 230760 (The Pile)

Max Activating Token Index: 939

Text #2

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4346. Min Act: -0.0000

Data Index: 214887 (The Pile)

Max Activating Token Index: 948

Text #3

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3937. Min Act: -0.0000

Data Index: 457925 (The Pile)

Max Activating Token Index: 408

Text #4

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.4083. Min Act: -0.0000

Data Index: 730698 (The Pile)

Max Activating Token Index: 836

Text #5

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3595. Min Act: -0.0000

Data Index: 1674176 (The Pile)

Max Activating Token Index: 173

Text #6

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3740. Min Act: -0.0000

Data Index: 59599 (The Pile)

Max Activating Token Index: 316

Text #7

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3387. Min Act: -0.0000

Data Index: 819954 (The Pile)

Max Activating Token Index: 405

Text #8

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3510. Min Act: -0.0000

Data Index: 229467 (The Pile)

Max Activating Token Index: 230

Text #9

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3614. Min Act: -0.0000

Data Index: 1709810 (The Pile)

Max Activating Token Index: 910

Text #10

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3454. Min Act: -0.0000

Data Index: 775875 (The Pile)

Max Activating Token Index: 490

Text #11

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3666. Min Act: -0.0000

Data Index: 299773 (The Pile)

Max Activating Token Index: 565

Text #12

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3500. Min Act: -0.0000

Data Index: 117897 (The Pile)

Max Activating Token Index: 909

Text #13

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3325. Min Act: -0.0000

Data Index: 827241 (The Pile)

Max Activating Token Index: 637

Text #14

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3688. Min Act: -0.0000

Data Index: 198877 (The Pile)

Max Activating Token Index: 547

Text #15

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3189. Min Act: -0.0000

Data Index: 812107 (The Pile)

Max Activating Token Index: 845

Text #16

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3132. Min Act: -0.0000

Data Index: 1903241 (The Pile)

Max Activating Token Index: 865

Text #17

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.2880. Min Act: -0.0000

Data Index: 1589530 (The Pile)

Max Activating Token Index: 371

Text #18

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.3205. Min Act: -0.0000

Data Index: 625506 (The Pile)

Max Activating Token Index: 433

Text #19

Max Range: 0.5224. Min Range: -0.5224

Max Act: 0.2941. Min Act: -0.0000

Data Index: 1239156 (The Pile)

Max Activating Token Index: 723