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

Dataset: The Pile

Neuron 671 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: 0.3516. Min Range: -0.3516

Max Act: 0.3516. Min Act: -0.0000

Data Index: 134347 (The Pile)

Max Activating Token Index: 307

Text #1

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.3409. Min Act: -0.0000

Data Index: 647263 (The Pile)

Max Activating Token Index: 155

Text #2

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.3014. Min Act: -0.0000

Data Index: 171954 (The Pile)

Max Activating Token Index: 239

Text #3

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2709. Min Act: -0.0000

Data Index: 1604610 (The Pile)

Max Activating Token Index: 889

Text #4

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2831. Min Act: -0.0000

Data Index: 1272632 (The Pile)

Max Activating Token Index: 542

Text #5

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2766. Min Act: -0.0000

Data Index: 584319 (The Pile)

Max Activating Token Index: 516

Text #6

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2473. Min Act: -0.0000

Data Index: 1921119 (The Pile)

Max Activating Token Index: 336

Text #7

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2194. Min Act: -0.0000

Data Index: 364273 (The Pile)

Max Activating Token Index: 783

Text #8

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2370. Min Act: -0.0000

Data Index: 1049278 (The Pile)

Max Activating Token Index: 863

Text #9

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2445. Min Act: -0.0000

Data Index: 1704749 (The Pile)

Max Activating Token Index: 582

Text #10

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2228. Min Act: -0.0000

Data Index: 406896 (The Pile)

Max Activating Token Index: 16

Text #11

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1411208 (The Pile)

Max Activating Token Index: 10

Text #12

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2201. Min Act: -0.0000

Data Index: 316976 (The Pile)

Max Activating Token Index: 258

Text #13

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2306. Min Act: -0.0000

Data Index: 191181 (The Pile)

Max Activating Token Index: 669

Text #14

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2478. Min Act: -0.0000

Data Index: 42202 (The Pile)

Max Activating Token Index: 529

Text #15

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2193. Min Act: -0.0000

Data Index: 595522 (The Pile)

Max Activating Token Index: 172

Text #16

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2161. Min Act: -0.0000

Data Index: 672435 (The Pile)

Max Activating Token Index: 903

Text #17

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.2287. Min Act: -0.0000

Data Index: 41346 (The Pile)

Max Activating Token Index: 11

Text #18

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.1831. Min Act: -0.0000

Data Index: 17526 (The Pile)

Max Activating Token Index: 104

Text #19

Max Range: 0.3516. Min Range: -0.3516

Max Act: 0.1992. Min Act: -0.0000

Data Index: 620739 (The Pile)

Max Activating Token Index: 383