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

Dataset: The Pile

Neuron 4372 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0556. Min Act: -0.0000

Data Index: 1879964 (The Pile)

Max Activating Token Index: 3

Text #1

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0512. Min Act: -0.0000

Data Index: 497778 (The Pile)

Max Activating Token Index: 5

Text #2

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0445. Min Act: -0.0000

Data Index: 1429696 (The Pile)

Max Activating Token Index: 19

Text #3

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0429. Min Act: -0.0000

Data Index: 988327 (The Pile)

Max Activating Token Index: 7

Text #4

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0437. Min Act: -0.0000

Data Index: 1606916 (The Pile)

Max Activating Token Index: 4

Text #5

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0415. Min Act: -0.0000

Data Index: 1446405 (The Pile)

Max Activating Token Index: 18

Text #6

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0423. Min Act: 0.0000

Data Index: 647915 (The Pile)

Max Activating Token Index: 6

Text #7

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0406. Min Act: -0.0000

Data Index: 1802109 (The Pile)

Max Activating Token Index: 821

Text #8

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0389. Min Act: -0.0000

Data Index: 1299246 (The Pile)

Max Activating Token Index: 4

Text #9

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0401. Min Act: -0.0000

Data Index: 1082024 (The Pile)

Max Activating Token Index: 12

Text #10

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0380. Min Act: -0.0000

Data Index: 1669999 (The Pile)

Max Activating Token Index: 9

Text #11

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0374. Min Act: -0.0000

Data Index: 1726430 (The Pile)

Max Activating Token Index: 26

Text #12

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0369. Min Act: -0.0000

Data Index: 1614330 (The Pile)

Max Activating Token Index: 28

Text #13

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0367. Min Act: -0.0000

Data Index: 1389169 (The Pile)

Max Activating Token Index: 23

Text #14

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0373. Min Act: -0.0000

Data Index: 105621 (The Pile)

Max Activating Token Index: 16

Text #15

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0335. Min Act: -0.0000

Data Index: 1886403 (The Pile)

Max Activating Token Index: 37

Text #16

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0360. Min Act: -0.0000

Data Index: 1940206 (The Pile)

Max Activating Token Index: 337

Text #17

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0347. Min Act: -0.0000

Data Index: 136125 (The Pile)

Max Activating Token Index: 944

Text #18

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0346. Min Act: -0.0000

Data Index: 617141 (The Pile)

Max Activating Token Index: 1005

Text #19

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0341. Min Act: -0.0000

Data Index: 1599274 (The Pile)

Max Activating Token Index: 36