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

Dataset: The Pile

Neuron 2758 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0317. Min Act: -0.0001

Data Index: 655375 (The Pile)

Max Activating Token Index: 13

Text #1

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0314. Min Act: -0.0000

Data Index: 243682 (The Pile)

Max Activating Token Index: 13

Text #2

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0313. Min Act: -0.0000

Data Index: 1830733 (The Pile)

Max Activating Token Index: 169

Text #3

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0325. Min Act: 0.0000

Data Index: 499627 (The Pile)

Max Activating Token Index: 6

Text #4

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0314. Min Act: -0.0000

Data Index: 958144 (The Pile)

Max Activating Token Index: 10

Text #5

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0311. Min Act: -0.0001

Data Index: 121814 (The Pile)

Max Activating Token Index: 13

Text #6

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0308. Min Act: 0.0000

Data Index: 1877334 (The Pile)

Max Activating Token Index: 28

Text #7

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0302. Min Act: -0.0000

Data Index: 1730173 (The Pile)

Max Activating Token Index: 27

Text #8

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0290. Min Act: -0.0000

Data Index: 80578 (The Pile)

Max Activating Token Index: 10

Text #9

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0299. Min Act: 0.0000

Data Index: 999343 (The Pile)

Max Activating Token Index: 5

Text #10

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0295. Min Act: -0.0000

Data Index: 1498693 (The Pile)

Max Activating Token Index: 9

Text #11

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0292. Min Act: -0.0000

Data Index: 876917 (The Pile)

Max Activating Token Index: 6

Text #12

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0292. Min Act: 0.0000

Data Index: 1063899 (The Pile)

Max Activating Token Index: 10

Text #13

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0289. Min Act: -0.0000

Data Index: 195699 (The Pile)

Max Activating Token Index: 13

Text #14

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0286. Min Act: -0.0000

Data Index: 53629 (The Pile)

Max Activating Token Index: 13

Text #15

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0283. Min Act: -0.0000

Data Index: 624927 (The Pile)

Max Activating Token Index: 991

Text #16

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0281. Min Act: 0.0000

Data Index: 1650983 (The Pile)

Max Activating Token Index: 1012

Text #17

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0290. Min Act: -0.0001

Data Index: 775670 (The Pile)

Max Activating Token Index: 10

Text #18

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0281. Min Act: -0.0000

Data Index: 955767 (The Pile)

Max Activating Token Index: 13

Text #19

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0279. Min Act: -0.0000

Data Index: 1972947 (The Pile)

Max Activating Token Index: 21