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

Dataset: The Pile

Neuron 3311 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.4373. Min Act: -0.0000

Data Index: 1400514 (The Pile)

Max Activating Token Index: 266

Text #1

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.4176. Min Act: -0.0000

Data Index: 484581 (The Pile)

Max Activating Token Index: 284

Text #2

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3516. Min Act: -0.0000

Data Index: 1864410 (The Pile)

Max Activating Token Index: 388

Text #3

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3560. Min Act: -0.0000

Data Index: 1105714 (The Pile)

Max Activating Token Index: 911

Text #4

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3641. Min Act: -0.0000

Data Index: 290666 (The Pile)

Max Activating Token Index: 235

Text #5

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2686. Min Act: 0.0000

Data Index: 1389716 (The Pile)

Max Activating Token Index: 895

Text #6

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3207. Min Act: -0.0000

Data Index: 1879898 (The Pile)

Max Activating Token Index: 217

Text #7

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3174. Min Act: -0.0000

Data Index: 1477576 (The Pile)

Max Activating Token Index: 162

Text #8

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3012. Min Act: -0.0000

Data Index: 383169 (The Pile)

Max Activating Token Index: 261

Text #9

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2886. Min Act: -0.0000

Data Index: 1995902 (The Pile)

Max Activating Token Index: 10

Text #10

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3374. Min Act: -0.0000

Data Index: 1090988 (The Pile)

Max Activating Token Index: 607

Text #11

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3065. Min Act: -0.0000

Data Index: 1142 (The Pile)

Max Activating Token Index: 703

Text #12

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2963. Min Act: -0.0000

Data Index: 1688766 (The Pile)

Max Activating Token Index: 306

Text #13

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.3173. Min Act: 0.0000

Data Index: 365311 (The Pile)

Max Activating Token Index: 682

Text #14

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2910. Min Act: -0.0000

Data Index: 258554 (The Pile)

Max Activating Token Index: 882

Text #15

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2838. Min Act: -0.0000

Data Index: 1940459 (The Pile)

Max Activating Token Index: 161

Text #16

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2833. Min Act: 0.0000

Data Index: 1623599 (The Pile)

Max Activating Token Index: 369

Text #17

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2759. Min Act: -0.0000

Data Index: 98531 (The Pile)

Max Activating Token Index: 95

Text #18

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2630. Min Act: -0.0000

Data Index: 333483 (The Pile)

Max Activating Token Index: 234

Text #19

Max Range: 0.4373. Min Range: -0.4373

Max Act: 0.2812. Min Act: -0.0000

Data Index: 1705876 (The Pile)

Max Activating Token Index: 468