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

Dataset: The Pile

Neuron 1055 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1294425 (The Pile)

Max Activating Token Index: 243

Text #1

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1394401 (The Pile)

Max Activating Token Index: 610

Text #2

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.6955. Min Act: -0.0000

Data Index: 643630 (The Pile)

Max Activating Token Index: 26

Text #3

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.7129. Min Act: 0.0000

Data Index: 1771579 (The Pile)

Max Activating Token Index: 292

Text #4

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.6862. Min Act: -0.0000

Data Index: 674396 (The Pile)

Max Activating Token Index: 700

Text #5

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.6009. Min Act: 0.0000

Data Index: 310543 (The Pile)

Max Activating Token Index: 701

Text #6

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.6626. Min Act: -0.0000

Data Index: 198686 (The Pile)

Max Activating Token Index: 899

Text #7

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1807033 (The Pile)

Max Activating Token Index: 176

Text #8

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5637. Min Act: -0.0000

Data Index: 1080409 (The Pile)

Max Activating Token Index: 927

Text #9

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5910. Min Act: -0.0000

Data Index: 1525987 (The Pile)

Max Activating Token Index: 660

Text #10

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5855. Min Act: -0.0000

Data Index: 1513870 (The Pile)

Max Activating Token Index: 439

Text #11

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5373. Min Act: -0.0000

Data Index: 1418958 (The Pile)

Max Activating Token Index: 917

Text #12

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5481. Min Act: -0.0000

Data Index: 229502 (The Pile)

Max Activating Token Index: 512

Text #13

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5157. Min Act: 0.0000

Data Index: 77889 (The Pile)

Max Activating Token Index: 417

Text #14

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5296. Min Act: -0.0000

Data Index: 1915241 (The Pile)

Max Activating Token Index: 846

Text #15

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.4716. Min Act: -0.0000

Data Index: 1990890 (The Pile)

Max Activating Token Index: 671

Text #16

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5380. Min Act: -0.0000

Data Index: 634090 (The Pile)

Max Activating Token Index: 717

Text #17

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5343. Min Act: -0.0000

Data Index: 1121501 (The Pile)

Max Activating Token Index: 91

Text #18

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5016. Min Act: -0.0000

Data Index: 1082314 (The Pile)

Max Activating Token Index: 488

Text #19

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.4894. Min Act: -0.0000

Data Index: 1507973 (The Pile)

Max Activating Token Index: 263