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

Dataset: The Pile

Neuron 3887 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: 0.9248. Min Range: -0.9248

Max Act: 0.9248. Min Act: -0.0000

Data Index: 516947 (The Pile)

Max Activating Token Index: 300

Text #1

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.9022. Min Act: -0.0000

Data Index: 1165668 (The Pile)

Max Activating Token Index: 778

Text #2

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8411. Min Act: -0.0000

Data Index: 1423026 (The Pile)

Max Activating Token Index: 67

Text #3

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.9093. Min Act: 0.0000

Data Index: 1324397 (The Pile)

Max Activating Token Index: 218

Text #4

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.6980. Min Act: -0.0000

Data Index: 1054155 (The Pile)

Max Activating Token Index: 613

Text #5

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.8327. Min Act: -0.0000

Data Index: 1518869 (The Pile)

Max Activating Token Index: 459

Text #6

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.7156. Min Act: -0.0000

Data Index: 1596421 (The Pile)

Max Activating Token Index: 395

Text #7

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.6888. Min Act: -0.0000

Data Index: 756949 (The Pile)

Max Activating Token Index: 605

Text #8

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1833666 (The Pile)

Max Activating Token Index: 361

Text #9

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.6350. Min Act: -0.0000

Data Index: 1848842 (The Pile)

Max Activating Token Index: 66

Text #10

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.6317. Min Act: -0.0000

Data Index: 1853175 (The Pile)

Max Activating Token Index: 363

Text #11

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.6638. Min Act: 0.0000

Data Index: 589356 (The Pile)

Max Activating Token Index: 942

Text #12

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.6311. Min Act: -0.0000

Data Index: 1417694 (The Pile)

Max Activating Token Index: 603

Text #13

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.5896. Min Act: -0.0000

Data Index: 909615 (The Pile)

Max Activating Token Index: 210

Text #14

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.5445. Min Act: -0.0000

Data Index: 723870 (The Pile)

Max Activating Token Index: 820

Text #15

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.6889. Min Act: -0.0000

Data Index: 5158 (The Pile)

Max Activating Token Index: 652

Text #16

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.5979. Min Act: -0.0000

Data Index: 1430625 (The Pile)

Max Activating Token Index: 587

Text #17

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.5878. Min Act: -0.0000

Data Index: 324711 (The Pile)

Max Activating Token Index: 1003

Text #18

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.6096. Min Act: 0.0000

Data Index: 354306 (The Pile)

Max Activating Token Index: 1011

Text #19

Max Range: 0.9248. Min Range: -0.9248

Max Act: 0.5995. Min Act: -0.0000

Data Index: 544664 (The Pile)

Max Activating Token Index: 1022